CN111580685A - Mongolian input method and input method system - Google Patents
Mongolian input method and input method system Download PDFInfo
- Publication number
- CN111580685A CN111580685A CN202010418732.8A CN202010418732A CN111580685A CN 111580685 A CN111580685 A CN 111580685A CN 202010418732 A CN202010418732 A CN 202010418732A CN 111580685 A CN111580685 A CN 111580685A
- Authority
- CN
- China
- Prior art keywords
- mongolian
- character string
- input method
- word
- matched
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/02—Input arrangements using manually operated switches, e.g. using keyboards or dials
- G06F3/023—Arrangements for converting discrete items of information into a coded form, e.g. arrangements for interpreting keyboard generated codes as alphanumeric codes, operand codes or instruction codes
- G06F3/0233—Character input methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/02—Input arrangements using manually operated switches, e.g. using keyboards or dials
- G06F3/023—Arrangements for converting discrete items of information into a coded form, e.g. arrangements for interpreting keyboard generated codes as alphanumeric codes, operand codes or instruction codes
- G06F3/0233—Character input methods
- G06F3/0236—Character input methods using selection techniques to select from displayed items
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Document Processing Apparatus (AREA)
Abstract
The invention provides a Mongolian input method and an input method system, wherein after a character string input by a user is received, a proper input method is automatically matched by analyzing the characteristics of the character string, and when the character string contains a slash, a crown is connected with the input method to input Mongolian double-root words; when the character string contains capital letters, the Mongolian borrowing is input by adopting a case-distinguished input method; when the character string contains the semicolon, a Mongolian word consisting of the word and the additional component is input by adopting a connection input method; under the condition that the character string does not contain slashes, capital letters and semicolons, a word input method is adopted, and when the input methods cannot be matched with proper Mongolian words, a keyboard mapping input method is adopted. Therefore, no matter which type of Mongolian words are input by the user, the Mongolian words can be accurately and efficiently output by adopting the corresponding input method, and the method is not limited by the borrow and the pronunciation of the user in different regions.
Description
Technical Field
The invention relates to the technical field of data input, in particular to a Mongolian input method and an input method system.
Background
At present, the Mongolian input method is generally divided into two types, the first type is an integral word input method using a word bank, and the second type is a pronunciation input method or a syllable input method through keyboard mapping, and similar to an English input method, letters are directly input through a keyboard.
The whole word input method can only output Mongolian words in a word bank, and cannot output borrowed words outside the word bank. The keyboard mapping input method can directly convert the character string inputted by the user through the keyboard into the Mongolian word by using different algorithms, but the vowel and the consonant in the Mongolian written language have homomorphic letters, and the pronunciation of each region in the spoken language is different, for example: some of the regional cogoup pronounces ondol in spoken language, and some of the regional cogoup pronounces undu in spoken language, so that different users may have errors in their mongol words that are output by keymap input methods affected by spoken language.
Therefore, the existing Mongolian input method cannot accurately and efficiently output Mongolian.
Disclosure of Invention
In view of the above, the invention provides a Mongolian input method and an input method system, which can realize accurate and efficient Mongolian output.
In order to achieve the above purpose, the invention provides the following specific technical scheme:
a method of inputting a mongolian character comprising:
receiving a character string input by a user through a keyboard;
judging whether the character string contains a slash or not;
if the stroke is included, determining that the target input method corresponding to the character string is a prefix connection input method and is used for inputting Mongolian double-root words;
if not, judging whether the character string contains capital letters;
if the capital letters are included, determining that the target input method corresponding to the character string is a case-distinguished input method and is used for inputting Mongolian borrowed words;
if not, judging whether the character string contains a semicolon;
if yes, determining that the target input method corresponding to the character string is a connection input method, and determining that the part behind the semicolon is an additional component, wherein the additional component comprises a lattice, a collage and a plurality of numbers;
if the split number is not included, determining that the target input method corresponding to the character string is a word input method;
if the corresponding Mongolian words are not matched for the character strings from the word code table by adopting the word input method, determining that the target input method corresponding to the character strings is a connection input method, and determining word parts and additional component parts in the character strings;
if the corresponding Mongolian word is not matched with the character string by adopting the connection input method, determining that the target input method corresponding to the character string is a keyboard mapping input method;
and executing the target input method, and outputting a candidate item list corresponding to the character string.
Optionally, when the target input method is a prefix connection input method, the executing the target input method and outputting a candidate list corresponding to the character string includes:
matching the sub-character strings at two sides of the slash with the Mongolian words from the word code table;
and connecting the Mongolian words matched with the sub-character strings on the two sides of the slash into one Mongolian word which is taken as a candidate item corresponding to the character string and output to the candidate item list.
Optionally, when the target input method is a prefix connection input method, the executing the target input method and outputting a candidate list corresponding to the character string includes:
matching the sub-character strings at two sides of the slash with the Mongolian words from the word code table;
if the corresponding Mongolian word is not matched, correcting the substring which is not matched with the result;
matching the corrected substrings with the Mongolian words from the word code table;
if the corresponding Mongolian word is matched, connecting the Mongolian words matched with the substrings on the two sides of the slash into one Mongolian word which is used as a candidate item corresponding to the character string and output to a candidate item list;
if the corresponding Mongolian word is not matched, determining a word part and an additional component part in the character string by adopting a connection input method, and matching the Mongolian word with the character string;
if the matching is successful, combining the matched Mongolian words and Mongolian additional components into candidate items corresponding to the character strings, and outputting the candidate items to a candidate item list;
if the matching fails, converting the character string into a Mongolian letter string by adopting a keyboard mapping input method according to a preset mapping relation between the characters in the keyboard and the Mongolian letters;
and outputting the Mongolian character string as a candidate corresponding to the character string to a candidate list.
Optionally, when the target input method is a case-specific input method, the executing the target input method to output a candidate list corresponding to the character string includes:
matching corresponding Mongolian words for the character strings from a word code table;
if the corresponding word is matched, determining positive vowels and negative vowels in the Mongolian according to upper and lower case letters in the character string, and outputting the Mongolian word as a candidate corresponding to the character string to a candidate list according to the output rule of syllable-ending consonants N after the positive vowels and the negative vowels;
if the corresponding Mongolian word is not matched, converting the character string into a Mongolian letter string by adopting a keyboard mapping input method according to a preset mapping relation between the characters in the keyboard and the Mongolian letters;
and outputting the Mongolian letter string as a candidate corresponding to the character string to a candidate list.
Optionally, when the target input method is a word input method, the executing the target input method and outputting a candidate list corresponding to the character string includes:
matching corresponding Mongolian words for the character strings from a word code table;
if the corresponding Mongolian word is matched, the matched Mongolian word is taken as a candidate item corresponding to the character string and is output to a candidate item list;
if the corresponding Mongolian word is not matched, correcting the character string;
matching the corrected character string with a Mongolian word from the word code table;
if the corresponding Mongolian word is matched, the matched Mongolian word is taken as a candidate item corresponding to the character string and is output to a candidate item list;
if the corresponding Mongolian word is not matched, determining a word part and an additional component part in the character string by adopting a connection input method, and matching the Mongolian word with the character string;
if the matching is successful, combining the matched Mongolian words and Mongolian additional components into candidate items corresponding to the character strings, and outputting the candidate items to a candidate item list;
if the matching fails, converting the character string into a Mongolian letter string by adopting a keyboard mapping input method according to a preset mapping relation between the characters in the keyboard and the Mongolian letters;
and outputting the Mongolian character string as a candidate corresponding to the character string to a candidate list.
Optionally, when the target input method is a connection input method, the executing the target input method and outputting a candidate list corresponding to the character string includes:
segmenting the character string from the last character of the character string to obtain a word part and an additional component part;
matching a Mongolian word from a word code table for the word part, and matching a Mongolian additional component from an additional component code table for the additional component part;
if the matching is successful, combining the matched Mongolian words and Mongolian additional components into candidate items corresponding to the character strings, and outputting the candidate items to a candidate item list;
if the matching is not successful, judging whether the character string is segmented to the third character from the left;
if not, correcting the character string to obtain a corrected character string, and returning to execute the step of starting to segment the character string from the last character of the character string;
if so, converting the character string into a Mongolian letter string by adopting a keyboard mapping input method according to a preset mapping relation between the characters in the keyboard and the Mongolian letters;
and outputting the Mongolian letter string as a candidate corresponding to the character string to a candidate list.
A mongolian input method system comprising:
the character string receiving unit is used for receiving a character string input by a user through a keyboard;
an input method determination unit for determining whether the character string includes a slash; if the stroke is included, determining that the target input method corresponding to the character string is a prefix connection input method and is used for inputting Mongolian double-root words; if not, judging whether the character string contains capital letters; if the capital letters are included, determining that the target input method corresponding to the character string is a case-distinguished input method and is used for inputting Mongolian borrowed words; if not, judging whether the character string contains a semicolon; if yes, determining that the target input method corresponding to the character string is a connection input method, and determining that the part behind the semicolon is an additional component, wherein the additional component comprises a lattice, a collage and a plurality of numbers; if the split number is not included, determining that the target input method corresponding to the character string is a word input method; if the corresponding Mongolian words are not matched for the character strings from the word code table by adopting the word input method, determining that the target input method corresponding to the character strings is a connection input method, and determining the word part and the additional component part of the character strings; if the corresponding Mongolian word is not matched with the character string by adopting the connection input method, determining that the target input method corresponding to the character string is a keyboard mapping input method;
and the input method execution unit is used for executing the target input method and outputting a candidate item list corresponding to the character string.
Optionally, the input method execution unit is specifically configured to:
when the target input method is a prefix connection input method, matching Mongolian words with sub-character strings on two sides of a slash from a word code table;
and connecting the Mongolian words matched with the sub-character strings on the two sides of the slash into one Mongolian word which is taken as a candidate item corresponding to the character string and output to the candidate item list.
Optionally, the input method execution unit is specifically configured to:
when the target input method is a prefix connection input method, matching Mongolian words with sub-character strings on two sides of a slash from a word code table;
if the corresponding Mongolian word is not matched, correcting the substring which is not matched with the result;
matching the corrected substrings with the Mongolian words from the word code table;
if the corresponding Mongolian word is matched, connecting the Mongolian words matched with the substrings on the two sides of the slash into one Mongolian word which is used as a candidate item corresponding to the character string and output to a candidate item list;
if the corresponding Mongolian word is not matched, determining a word part and an additional component part in the character string by adopting a connection input method, and matching the Mongolian word with the character string;
if the matching is successful, combining the matched Mongolian words and Mongolian additional components into candidate items corresponding to the character strings, and outputting the candidate items to a candidate item list;
if the matching fails, converting the character string into a Mongolian letter string by adopting a keyboard mapping input method according to a preset mapping relation between the characters in the keyboard and the Mongolian letters;
and outputting the Mongolian character string as a candidate corresponding to the character string to a candidate list.
Optionally, the input method execution unit is specifically configured to:
when the target input method is a case-distinguished input method, matching corresponding Mongolian words for the character strings from a word code table;
if the corresponding word is matched, determining positive vowels and negative vowels in the Mongolian according to upper and lower case letters in the character string, and outputting the Mongolian word as a candidate corresponding to the character string to a candidate list according to the output rule of syllable-ending consonants N after the positive vowels and the negative vowels;
if the corresponding Mongolian word is not matched, converting the character string into a Mongolian letter string by adopting a keyboard mapping input method according to a preset mapping relation between the characters in the keyboard and the Mongolian letters;
and outputting the Mongolian letter string as a candidate corresponding to the character string to a candidate list.
Optionally, the input method execution unit is specifically configured to:
when the target input method is a word input method, matching corresponding Mongolian words for the character strings from a word code table;
if the corresponding Mongolian word is matched, the matched Mongolian word is taken as a candidate item corresponding to the character string and is output to a candidate item list;
if the corresponding Mongolian word is not matched, correcting the character string;
matching the corrected character string with a Mongolian word from the word code table;
if the corresponding Mongolian word is matched, the matched Mongolian word is taken as a candidate item corresponding to the character string and is output to a candidate item list;
if the corresponding Mongolian word is not matched, determining a word part and an additional component part in the character string by adopting a connection input method, and matching the Mongolian word with the character string;
if the matching is successful, combining the matched Mongolian words and Mongolian additional components into candidate items corresponding to the character strings, and outputting the candidate items to a candidate item list;
if the matching fails, converting the character string into a Mongolian letter string by adopting a keyboard mapping input method according to a preset mapping relation between the characters in the keyboard and the Mongolian letters;
and outputting the Mongolian character string as a candidate corresponding to the character string to a candidate list.
Optionally, the input method execution unit is specifically configured to:
when the target input method is a connection input method, segmenting the character string from the last character of the character string to obtain a word part and an additional component part;
matching a Mongolian word from a word code table for the word part, and matching a Mongolian additional component from an additional component code table for the additional component part;
if the matching is successful, combining the matched Mongolian words and Mongolian additional components into candidate items corresponding to the character strings, and outputting the candidate items to a candidate item list;
if the matching is not successful, judging whether the character string is segmented to the third character from the left;
if not, correcting the character string to obtain a corrected character string, and returning to execute the step of starting to segment the character string from the last character of the character string;
if so, converting the character string into a Mongolian letter string by adopting a keyboard mapping input method according to a preset mapping relation between the characters in the keyboard and the Mongolian letters;
and outputting the Mongolian letter string as a candidate corresponding to the character string to a candidate list.
Compared with the prior art, the invention has the following beneficial effects:
the invention discloses a Mongolian input method, which comprises the steps of receiving a character string input by a user, automatically matching a proper input method by analyzing the characteristics of the character string, and inputting Mongolian double-root words by adopting a crown connection input method when the character string comprises a slash; when the character string contains capital letters, the Mongolian borrowing is input by adopting a case-distinguished input method; when the character string contains the semicolon, a Mongolian word consisting of the word and the additional component is input by adopting a connection input method; in the case that the character string does not contain slashes, capital letters and semicolons, a word input method is adopted. Therefore, no matter which type of Mongolian words are input by the user, the Mongolian words can be accurately and efficiently output by adopting the corresponding input method, and the method is not limited by the borrow and the pronunciation of the user in different regions.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
FIG. 1 is a schematic flow chart of a Mongolian input method according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of another Mongolian input method disclosed in the embodiments of the present invention;
fig. 3 is a schematic structural diagram of a Mongolian input method system according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The inventor finds out through research that: the Mongolian is a character with adhesiveness, but has no prefix, only suffix, and has the characteristics that the fixed head and the fixed tail of a word are not fixed, and nouns such as names of people and place are used for writing two words in series by using word crowns, additional components such as noun lattices, leaders and complex numbers are used for writing in series with word stems by using Mongolian blanks, and the words are not communicated with the Mongolian characters for distinguishing the shape-changing rules of letters. The invention provides a crown connection input method for connecting two words through crowns, a case-distinguished input method for inputting borrows, a connection input method for connecting word stems with additional components, a word input method and a keyboard mapping input method according to the characteristics of Mongolian, and Mongolian and Chinese mutual writing input and Mongolian and Sirillic can be realized through the connection methods.
Specifically, referring to fig. 1, the method for inputting a Mongolian disclosed in this embodiment includes the following steps:
s101: receiving a character string input by a user through a keyboard;
s102: judging whether the character string contains a slash;
if yes, executing S103: determining a target input method corresponding to the character string as a prefix connection input method for inputting Mongolian double-root words;
it should be noted that the slash in the character string input by the user represents the prefix, two words can be connected through the prefix, and the words on both sides of the prefix respectively keep the positive lexical rule of the Mongolian, so the Mongolian words input by adopting the prefix connection input method can be composed of yin and yang words, and the prefix is carried by the word behind the prefix, so that the initial syllable attribute is naturally kept.
If not, executing S104: judging whether the character string contains capital letters;
if the capital letters are included, execute S105: determining a target input method corresponding to the character string as a case-distinguished input method for inputting Mongolian borrowed words;
in the embodiment, the case-distinguished input method is used for inputting the borrowed words, when the case-distinguished input method is used for inputting the borrowed words, the positive vowels and the negative vowels in the Mongolian are determined according to the case letters in the character string, and the final consonants N of the syllables input later are determined to have no points according to the output rule of the final consonants N after the positive vowels and the negative vowels.
If not, executing S106: judging whether the character string contains a semicolon;
if yes, executing S107: determining a target input method corresponding to the character string as a connection input method, and determining the rear part of the semicolon as an additional component, wherein the additional component comprises a lattice, a collage and a plurality of numbers;
the user inputs a word formed by connecting a word part and an additional component part by inputting a character string comprising a part number, the word part and the additional component part are connected into a word according to the rules of a Mongolian orthography, the part number in the character string input by the user represents a part writing symbol of the Mongolian additional component, and the part writing symbol with the part number is an additional component formed by a lattice, a collage, a complex number and the like.
If not, executing S108: determining a target input method corresponding to the character string as a word input method;
s109: whether a result is matched from the word code table;
namely, the corresponding Mongolian words are matched for the character strings directly from the word code table by adopting the word input method.
If the result is not matched from the word code table, executing S107;
if the corresponding Mongolian word is not matched for the character string from the word code table by adopting the word input method, determining the target input method corresponding to the character string as a connection input method, and determining the word part and the additional component part in the character string.
S110: whether a connection input method is adopted to match the character string with the matching result or not is judged;
the character string is segmented into word parts and additional component parts by using a connection input method, corresponding Mongolian words are matched for the word parts from the word code table, and corresponding additional components are matched for the additional component parts from the additional component code table.
If the corresponding Mongolian word is not matched for the character string by adopting the connection input method, executing S111: determining a target input method corresponding to the character string as a keyboard mapping input method;
the keyboard mapping input method is to convert character strings which are not matched with results into Mongolian letter strings according to the preset mapping relation between characters in a keyboard and Mongolian letters.
S112: and executing the target input method and outputting a candidate item list corresponding to the character string.
It should be noted that, the execution method of each Mongolian input method is different, and the following description is made separately:
one, word crown connection input method
The vowel harmony of the orthographic method of the Mongolian is broken through when the modern Mongolian is a noun with fixed meanings such as place name, person name, object name and the like, yin and yang words can be continuously written into a double-root word, when the double-root word is input, the second word needs to keep the prefix crown of the first word and is changed into a form in the word, the first syllable keeps the attribute of the initial syllable, for example, (bayan/undur) (han/agvla) (vsv/turugqi) and the like, and the second root of the double-root word keeps the attribute of the initial syllable. The prefix connection input method is used for inputting double-root words, the slash in the character string input by the user represents the prefix, the prefix can be connected with two words, and when the character string input by the user contains the slash, the prefix connection input method is determined to be used.
Specifically, referring to fig. 2, when the target input method is a prefix connection input method, the method for executing the target input method and outputting the candidate list corresponding to the character string includes the following steps:
s203: dividing the character string into sub character strings at two sides of a slash by adopting a prefix connection input method;
s204: adopting a word input method;
matching the sub-character strings at two sides of the slash with the Mongolian words from the word code table;
s205: whether a result is matched from the word code table;
if the result is matched, execute S211: acquiring candidate items corresponding to the character strings and outputting a candidate item list corresponding to the character strings;
and connecting the Mongolian words matched with the sub-character strings on the two sides of the slash into one Mongolian word which is taken as a candidate item corresponding to the character string and output to the candidate item list.
If the result is not matched, execute S206: whether it has been corrected;
if not, go to step S207: correcting the character string;
essentially, the substrings that do not match the result are corrected, and step S204 is executed after correction, and the Mongolian words are matched for the corrected substrings from the word code table again by using the word input method.
If the correction is made, execute S208: determining a word part and an additional component part in the character string by adopting a connection input method, and matching Mongolian words for the character string;
s209: whether a connection input method is adopted for matching a result in the character string or not is judged;
if the result is not matched, executing S210: converting the character string into a Mongolian character string by adopting a keyboard mapping input method;
and converting the character string into a Mongolian letter string according to a preset mapping relation between the characters in the keyboard and the Mongolian letters.
S211: acquiring candidate items corresponding to the character strings and outputting a candidate item list corresponding to the character strings;
namely, the Mongolian character string is taken as a candidate item and is output to a candidate item list.
If the result is matched, S211 is directly executed, the matched Mongolian word and Mongolian additional components are combined into a candidate corresponding to the character string, and the candidate is output to a candidate list.
Two, case-distinguished input method
The early-stage borrowing of Mongolian is completely generalized by Mongolian, only on modern Chinese, English and other foreign language borrowing, and particularly, when the name and place of a person are transcribed, the Mongolian letter system for borrowing words is used for writing. The usage rule of the Mongolian word borrowing letter system breaks through the vowel harmony rule of the Mongolian orthography rule, and the font emphasizes the shape recognition method, so that the vowels and the consonants of the foreign words are intuitively recognized, and the isomorphism problem is avoided. The case-distinguished input method disclosed by the invention reasonably calls a Mongolian word borrowing letter system. By case-by-case differentiating the borrowed words from Mongolian positive vowels and negative vowels, the last consonant N of the syllable input later is determined to have no point according to the positive and negative vowels, e.g.
Two words can see that the end syllable consonant N after a positive or neutral vowel has no point, while the end syllable consonant N after a negative vowel has a point. The specification of Mongolian letterThe context transformation relation of the Mongolian borrow omits the use of a control symbol in the input of the Mongolian borrow, such as the input of the existing input method
The input method of the word is elEmEn (fvs1) t, the case-distinguished input method of the invention inputs elEmEnt, and the use of control symbols is omitted by using case letters to standardize the foreign word-letter system of Mongolian characters.
Specifically, referring to fig. 2, when the target input method is a case-specific input method, the method for executing the target input method and outputting the candidate list corresponding to the character string includes the following steps:
s213: matching corresponding Mongolian words for the character strings from the word code table by adopting a case-distinguished input method;
s214: whether a result is matched;
if the corresponding word is matched, executing S211: and acquiring candidate items corresponding to the character strings and outputting a candidate item list corresponding to the character strings.
Outputting the Mongolian words matched from the word code table as candidate items corresponding to the character strings to a candidate item list;
if the corresponding Mongolian word is not matched, executing S210: converting the character string into a Mongolian character string by adopting a keyboard mapping input method;
converting the character string into a Mongolian letter string according to a preset mapping relation between the characters in the keyboard and the Mongolian letters;
s211: acquiring candidate items corresponding to the character strings and outputting a candidate item list corresponding to the character strings;
i.e. the mongolian alphabet string is output to the candidate list as a candidate corresponding to the character string.
Note that, when outputting the candidates, it is necessary to follow the principle that the final consonant N after the positive or neutral vowel has no point, and the final consonant N after the negative vowel has a point.
Three, word input method
Specifically, referring to fig. 2, when the target input method is a word input method, the method for executing the target input method and outputting the candidate list corresponding to the character string includes the following steps:
s204: adopting a word input method;
corresponding Mongolian words are matched for the character strings from the word code table.
S205: whether a result is matched from the word code table;
if the result is matched, execute S211: acquiring candidate items corresponding to the character strings and outputting a candidate item list corresponding to the character strings;
i.e. the matching mongolian word from the word code table is determined as a candidate corresponding to the character string.
If the result is not matched, execute S206: whether it has been corrected;
if not, go to step S207: correcting the character string;
essentially, the whole character string is corrected, S204 is executed after the correction, and the Mongolian words are matched for the corrected character string from the word code table by adopting the word input method again.
If the correction is made, execute S208: determining a word part and an additional component part in the character string by adopting a connection input method, and matching Mongolian words for the character string;
s209: whether a connection input method is adopted for matching a result in the character string or not is judged;
if the result is not matched, executing S210: converting the character string into a Mongolian character string by adopting a keyboard mapping input method;
and converting the character string into a Mongolian letter string according to a preset mapping relation between the characters in the keyboard and the Mongolian letters.
S211: acquiring candidate items corresponding to the character strings and outputting a candidate item list corresponding to the character strings;
namely, the Mongolian character string is taken as a candidate item and is output to a candidate item list.
If the result is matched, S211 is directly executed, the matched Mongolian word and Mongolian additional components are combined into a candidate corresponding to the character string, and the candidate is output to a candidate list.
Four, connection input method
Specifically, referring to fig. 2, when the target input method is a word input method, the method for executing the target input method and outputting the candidate list corresponding to the character string includes the following steps:
s208: determining a word part and an additional component part in the character string by adopting a connection input method, and matching Mongolian words for the character string;
segmenting the character string from the last character of the character string to obtain a word part and an additional component part;
matching Mongolian words for the word parts from the word code table, and matching Mongolian conjunctions for the additional component parts from the additional component code table;
and if the matching is successful, the result is matched by adopting a connection input method as the character string.
If the matching is not successful, judging whether the character string is segmented into a third character from the left;
if not, correcting the character string to obtain a corrected character string, and returning to execute the step of segmenting the character string from the last character of the character string;
if the third character from the left of the character string is segmented, the result is not matched for the character string by adopting the connection input method.
S209: whether the character string is matched with the result or not is determined by adopting a connection input method;
if the result is not matched, executing S210: converting the character string into a Mongolian character string by adopting a keyboard mapping input method;
and converting the character string into a Mongolian letter string according to a preset mapping relation between the characters in the keyboard and the Mongolian letters.
S211: acquiring candidate items corresponding to the character strings and outputting a candidate item list corresponding to the character strings;
namely, the Mongolian character string is taken as a candidate item and is output to a candidate item list.
And if the result is matched by adopting a connection input method, directly executing S211, combining the matched Mongolian words and Mongolian additional components into candidate items corresponding to the character string, and outputting the candidate items to a candidate item list.
Fifth, keyboard mapping input method
Specifically, according to a preset mapping relation between characters and Mongolian letters in the keyboard, the character strings are converted into Mongolian letter strings, and the Mongolian letter strings are used as candidate items corresponding to the character strings and output to a candidate item list.
Based on the Mongolian input method disclosed in the above embodiments, the embodiment correspondingly discloses a Mongolian input method system, please refer to FIG. 2, and the Mongolian input method system includes:
a character string receiving unit 201 for receiving a character string input by a user through a keyboard;
an input method determination unit 202 for determining whether the character string includes a slash; if the stroke is included, determining that the target input method corresponding to the character string is a prefix connection input method and is used for inputting Mongolian double-root words; if not, judging whether the character string contains capital letters; if the capital letters are included, determining that the target input method corresponding to the character string is a case-distinguished input method and is used for inputting Mongolian borrowed words; if not, judging whether the character string contains a semicolon; if yes, determining that the target input method corresponding to the character string is a connection input method, and determining that the part behind the semicolon is an additional component, wherein the additional component comprises a lattice, a collage and a plurality of numbers; if the split number is not included, determining that the target input method corresponding to the character string is a word input method; if the corresponding Mongolian words are not matched for the character strings from the word code table by adopting the word input method, determining that the target input method corresponding to the character strings is a connection input method, and determining the word part and the additional component part of the character strings; if the corresponding Mongolian word is not matched with the character string by adopting the connection input method, determining that the target input method corresponding to the character string is a keyboard mapping input method;
an input method execution unit 203 for executing the target input method and outputting a candidate list corresponding to the character string.
Optionally, the input method execution unit 203 is specifically configured to:
when the target input method is a prefix connection input method, matching Mongolian words with sub-character strings on two sides of a slash from a word code table;
and connecting the Mongolian words matched with the sub-character strings on the two sides of the slash into one Mongolian word which is taken as a candidate item corresponding to the character string and output to the candidate item list.
Optionally, the input method execution unit 203 is specifically configured to:
when the target input method is a prefix connection input method, matching Mongolian words with sub-character strings on two sides of a slash from a word code table;
if the corresponding Mongolian word is not matched, correcting the substring which is not matched with the result;
matching the corrected substrings with the Mongolian words from the word code table;
if the corresponding Mongolian word is matched, connecting the Mongolian words matched with the substrings on the two sides of the slash into one Mongolian word which is used as a candidate item corresponding to the character string and output to a candidate item list;
if the corresponding Mongolian word is not matched, determining a word part and an additional component part in the character string by adopting a connection input method, and matching the Mongolian word with the character string;
if the matching is successful, combining the matched Mongolian words and Mongolian additional components into candidate items corresponding to the character strings, and outputting the candidate items to a candidate item list;
if the matching fails, converting the character string into a Mongolian letter string by adopting a keyboard mapping input method according to a preset mapping relation between the characters in the keyboard and the Mongolian letters;
and outputting the Mongolian character string as a candidate corresponding to the character string to a candidate list.
Optionally, the input method execution unit 203 is specifically configured to:
when the target input method is a case-distinguished input method, matching corresponding Mongolian words for the character strings from a word code table;
if the corresponding word is matched, determining positive vowels and negative vowels in the Mongolian according to upper and lower case letters in the character string, and outputting the Mongolian word as a candidate corresponding to the character string to a candidate list according to the output rule of syllable-ending consonants N after the positive vowels and the negative vowels;
if the corresponding Mongolian word is not matched, converting the character string into a Mongolian letter string by adopting a keyboard mapping input method according to a preset mapping relation between the characters in the keyboard and the Mongolian letters;
and outputting the Mongolian letter string as a candidate corresponding to the character string to a candidate list.
Optionally, the input method execution unit 203 is specifically configured to:
when the target input method is a word input method, matching corresponding Mongolian words for the character strings from a word code table;
if the corresponding Mongolian word is matched, the matched Mongolian word is taken as a candidate item corresponding to the character string and is output to a candidate item list;
if the corresponding Mongolian word is not matched, correcting the character string;
matching the corrected character string with a Mongolian word from the word code table;
if the corresponding Mongolian word is matched, the matched Mongolian word is taken as a candidate item corresponding to the character string and is output to a candidate item list;
if the corresponding Mongolian word is not matched, determining a word part and an additional component part in the character string by adopting a connection input method, and matching the Mongolian word with the character string;
if the matching is successful, combining the matched Mongolian words and Mongolian additional components into candidate items corresponding to the character strings, and outputting the candidate items to a candidate item list;
if the matching fails, converting the character string into a Mongolian letter string by adopting a keyboard mapping input method according to a preset mapping relation between the characters in the keyboard and the Mongolian letters;
and outputting the Mongolian character string as a candidate corresponding to the character string to a candidate list.
Optionally 203, the input method execution unit is specifically configured to:
when the target input method is a connection input method, segmenting the character string from the last character of the character string to obtain a word part and an additional component part;
matching a Mongolian word from a word code table for the word part, and matching a Mongolian additional component from an additional component code table for the additional component part;
if the matching is successful, combining the matched Mongolian words and Mongolian additional components into candidate items corresponding to the character strings, and outputting the candidate items to a candidate item list;
if the matching is not successful, judging whether the character string is segmented to the third character from the left;
if not, correcting the character string to obtain a corrected character string, and returning to execute the step of starting to segment the character string from the last character of the character string;
if so, converting the character string into a Mongolian letter string by adopting a keyboard mapping input method according to a preset mapping relation between the characters in the keyboard and the Mongolian letters;
and outputting the Mongolian letter string as a candidate corresponding to the character string to a candidate list.
According to the Mongolian input method system disclosed by the embodiment, after a character string input by a user is received, a proper input method is automatically matched by analyzing the characteristics of the character string, and when the character string contains a slash, a crown is connected with the input method to input Mongolian double-root words; when the character string contains capital letters, the Mongolian borrowing is input by adopting a case-distinguished input method; when the character string contains the semicolon, a Mongolian word consisting of the word and the additional component is input by adopting a connection input method; in the case that the character string does not contain slashes, capital letters and semicolons, a word input method is adopted. Therefore, no matter which type of Mongolian words are input by the user, the Mongolian words can be accurately and efficiently output by adopting the corresponding input method, and the method is not limited by the borrow and the pronunciation of the user in different regions.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (12)
1. A method of inputting a Mongolian, comprising:
receiving a character string input by a user through a keyboard;
judging whether the character string contains a slash or not;
if the stroke is included, determining that the target input method corresponding to the character string is a prefix connection input method and is used for inputting Mongolian double-root words;
if not, judging whether the character string contains capital letters;
if the capital letters are included, determining that the target input method corresponding to the character string is a case-distinguished input method and is used for inputting Mongolian borrowed words;
if not, judging whether the character string contains a semicolon;
if yes, determining that the target input method corresponding to the character string is a connection input method, and determining that the part behind the semicolon is an additional component, wherein the additional component comprises a lattice, a collage and a plurality of numbers;
if the split number is not included, determining that the target input method corresponding to the character string is a word input method;
if the corresponding Mongolian words are not matched for the character strings from the word code table by adopting the word input method, determining that the target input method corresponding to the character strings is a connection input method, and determining word parts and additional component parts in the character strings;
if the corresponding Mongolian word is not matched with the character string by adopting the connection input method, determining that the target input method corresponding to the character string is a keyboard mapping input method;
and executing the target input method, and outputting a candidate item list corresponding to the character string.
2. The method of claim 1, wherein when the target input method is a prefix-join input method, the executing the target input method to output a list of candidates corresponding to the string comprises:
matching the sub-character strings at two sides of the slash with the Mongolian words from the word code table;
and connecting the Mongolian words matched with the sub-character strings on the two sides of the slash into one Mongolian word which is taken as a candidate item corresponding to the character string and output to the candidate item list.
3. The method of claim 1, wherein when the target input method is a prefix-join input method, the executing the target input method to output a list of candidates corresponding to the string comprises:
matching the sub-character strings at two sides of the slash with the Mongolian words from the word code table;
if the corresponding Mongolian word is not matched, correcting the substring which is not matched with the result;
matching the corrected substrings with the Mongolian words from the word code table;
if the corresponding Mongolian word is matched, connecting the Mongolian words matched with the substrings on the two sides of the slash into one Mongolian word which is used as a candidate item corresponding to the character string and output to a candidate item list;
if the corresponding Mongolian word is not matched, determining a word part and an additional component part in the character string by adopting a connection input method, and matching the Mongolian word with the character string;
if the matching is successful, combining the matched Mongolian words and Mongolian additional components into candidate items corresponding to the character strings, and outputting the candidate items to a candidate item list;
if the matching fails, converting the character string into a Mongolian letter string by adopting a keyboard mapping input method according to a preset mapping relation between the characters in the keyboard and the Mongolian letters;
and outputting the Mongolian character string as a candidate corresponding to the character string to a candidate list.
4. The method of claim 1, wherein when the target input method is a case-sensitive input method, the executing the target input method to output a list of candidates corresponding to the string comprises:
matching corresponding Mongolian words for the character strings from a word code table;
if the corresponding word is matched, determining positive vowels and negative vowels in the Mongolian according to upper and lower case letters in the character string, and outputting the Mongolian word as a candidate corresponding to the character string to a candidate list according to the output rule of syllable-ending consonants N after the positive vowels and the negative vowels;
if the corresponding Mongolian word is not matched, converting the character string into a Mongolian letter string by adopting a keyboard mapping input method according to a preset mapping relation between the characters in the keyboard and the Mongolian letters;
and outputting the Mongolian letter string as a candidate corresponding to the character string to a candidate list.
5. The method of claim 1, wherein when the target input method is a word input method, the executing the target input method to output a list of candidates corresponding to the character string comprises:
matching corresponding Mongolian words for the character strings from a word code table;
if the corresponding Mongolian word is matched, the matched Mongolian word is taken as a candidate item corresponding to the character string and is output to a candidate item list;
if the corresponding Mongolian word is not matched, correcting the character string;
matching the corrected character string with a Mongolian word from the word code table;
if the corresponding Mongolian word is matched, the matched Mongolian word is taken as a candidate item corresponding to the character string and is output to a candidate item list;
if the corresponding Mongolian word is not matched, determining a word part and an additional component part in the character string by adopting a connection input method, and matching the Mongolian word with the character string;
if the matching is successful, combining the matched Mongolian words and Mongolian additional components into candidate items corresponding to the character strings, and outputting the candidate items to a candidate item list;
if the matching fails, converting the character string into a Mongolian letter string by adopting a keyboard mapping input method according to a preset mapping relation between the characters in the keyboard and the Mongolian letters;
and outputting the Mongolian character string as a candidate corresponding to the character string to a candidate list.
6. The method of claim 1, wherein when the target input method is a connection input method, the executing the target input method to output a list of candidates corresponding to the character string comprises:
segmenting the character string from the last character of the character string to obtain a word part and an additional component part;
matching a Mongolian word from a word code table for the word part, and matching a Mongolian additional component from an additional component code table for the additional component part;
if the matching is successful, combining the matched Mongolian words and Mongolian additional components into candidate items corresponding to the character strings, and outputting the candidate items to a candidate item list;
if the matching is not successful, judging whether the character string is segmented to the third character from the left;
if not, correcting the character string to obtain a corrected character string, and returning to execute the step of starting to segment the character string from the last character of the character string;
if so, converting the character string into a Mongolian letter string by adopting a keyboard mapping input method according to a preset mapping relation between the characters in the keyboard and the Mongolian letters;
and outputting the Mongolian letter string as a candidate corresponding to the character string to a candidate list.
7. A system for a mongolian input method, comprising:
the character string receiving unit is used for receiving a character string input by a user through a keyboard;
an input method determination unit for determining whether the character string includes a slash; if the stroke is included, determining that the target input method corresponding to the character string is a prefix connection input method and is used for inputting Mongolian double-root words; if not, judging whether the character string contains capital letters; if the capital letters are included, determining that the target input method corresponding to the character string is a case-distinguished input method and is used for inputting Mongolian borrowed words; if not, judging whether the character string contains a semicolon; if yes, determining that the target input method corresponding to the character string is a connection input method, and determining that the part behind the semicolon is an additional component, wherein the additional component comprises a lattice, a collage and a plurality of numbers; if the split number is not included, determining that the target input method corresponding to the character string is a word input method; if the corresponding Mongolian words are not matched for the character strings from the word code table by adopting the word input method, determining that the target input method corresponding to the character strings is a connection input method, and determining word parts and additional component parts in the character strings; if the corresponding Mongolian word is not matched with the character string by adopting the connection input method, determining that the target input method corresponding to the character string is a keyboard mapping input method;
and the input method execution unit is used for executing the target input method and outputting a candidate item list corresponding to the character string.
8. The system of claim 7, wherein the input method execution unit is specifically configured to:
when the target input method is a prefix connection input method, matching Mongolian words with sub-character strings on two sides of a slash from a word code table;
and connecting the Mongolian words matched with the sub-character strings on the two sides of the slash into one Mongolian word which is taken as a candidate item corresponding to the character string and output to the candidate item list.
9. The system of claim 7, wherein the input method execution unit is specifically configured to:
when the target input method is a prefix connection input method, matching Mongolian words with sub-character strings on two sides of a slash from a word code table;
if the corresponding Mongolian word is not matched, correcting the substring which is not matched with the result;
matching the corrected substrings with the Mongolian words from the word code table;
if the corresponding Mongolian word is matched, connecting the Mongolian words matched with the substrings on the two sides of the slash into one Mongolian word which is used as a candidate item corresponding to the character string and output to a candidate item list;
if the corresponding Mongolian word is not matched, determining a word part and an additional component part in the character string by adopting a connection input method, and matching the Mongolian word with the character string;
if the matching is successful, combining the matched Mongolian words and Mongolian additional components into candidate items corresponding to the character strings, and outputting the candidate items to a candidate item list;
if the matching fails, converting the character string into a Mongolian letter string by adopting a keyboard mapping input method according to a preset mapping relation between the characters in the keyboard and the Mongolian letters;
and outputting the Mongolian character string as a candidate corresponding to the character string to a candidate list.
10. The system of claim 7, wherein the input method execution unit is specifically configured to:
when the target input method is a case-distinguished input method, matching corresponding Mongolian words for the character strings from a word code table;
if the corresponding word is matched, determining positive vowels and negative vowels in the Mongolian according to upper and lower case letters in the character string, and outputting the Mongolian word as a candidate corresponding to the character string to a candidate list according to the output rule of syllable-ending consonants N after the positive vowels and the negative vowels;
if the corresponding Mongolian word is not matched, converting the character string into a Mongolian letter string by adopting a keyboard mapping input method according to a preset mapping relation between the characters in the keyboard and the Mongolian letters;
and outputting the Mongolian letter string as a candidate corresponding to the character string to a candidate list.
11. The system of claim 7, wherein the input method execution unit is specifically configured to:
when the target input method is a word input method, matching corresponding Mongolian words for the character strings from a word code table;
if the corresponding Mongolian word is matched, the matched Mongolian word is taken as a candidate item corresponding to the character string and is output to a candidate item list;
if the corresponding Mongolian word is not matched, correcting the character string;
matching the corrected character string with a Mongolian word from the word code table;
if the corresponding Mongolian word is matched, the matched Mongolian word is taken as a candidate item corresponding to the character string and is output to a candidate item list;
if the corresponding Mongolian word is not matched, determining a word part and an additional component part in the character string by adopting a connection input method, and matching the Mongolian word with the character string;
if the matching is successful, combining the matched Mongolian words and Mongolian additional components into candidate items corresponding to the character strings, and outputting the candidate items to a candidate item list;
if the matching fails, converting the character string into a Mongolian letter string by adopting a keyboard mapping input method according to a preset mapping relation between the characters in the keyboard and the Mongolian letters;
and outputting the Mongolian character string as a candidate corresponding to the character string to a candidate list.
12. The system of claim 7, wherein the input method execution unit is specifically configured to:
when the target input method is a connection input method, segmenting the character string from the last character of the character string to obtain a word part and an additional component part;
matching a Mongolian word from a word code table for the word part, and matching a Mongolian additional component from an additional component code table for the additional component part;
if the matching is successful, combining the matched Mongolian words and Mongolian additional components into candidate items corresponding to the character strings, and outputting the candidate items to a candidate item list;
if the matching is not successful, judging whether the character string is segmented to the third character from the left;
if not, correcting the character string to obtain a corrected character string, and returning to execute the step of starting to segment the character string from the last character of the character string;
if so, converting the character string into a Mongolian letter string by adopting a keyboard mapping input method according to a preset mapping relation between the characters in the keyboard and the Mongolian letters;
and outputting the Mongolian letter string as a candidate corresponding to the character string to a candidate list.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010418732.8A CN111580685B (en) | 2020-05-18 | 2020-05-18 | Mongolian input method and input method system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010418732.8A CN111580685B (en) | 2020-05-18 | 2020-05-18 | Mongolian input method and input method system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111580685A true CN111580685A (en) | 2020-08-25 |
| CN111580685B CN111580685B (en) | 2023-05-23 |
Family
ID=72123044
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010418732.8A Active CN111580685B (en) | 2020-05-18 | 2020-05-18 | Mongolian input method and input method system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111580685B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004206659A (en) * | 2002-11-07 | 2004-07-22 | Nippon Telegr & Teleph Corp <Ntt> | Reading information determination method, device, and program |
| CN1936791A (en) * | 2006-10-16 | 2007-03-28 | 孟和吉雅 | Mongol digital keyboard inputting method based on syllable |
| WO2008136647A1 (en) * | 2007-05-08 | 2008-11-13 | Young Jae Jung | A keypad array of mobile phone for inputting characters of russian language |
| CN102184031A (en) * | 2011-04-25 | 2011-09-14 | 内蒙古大学 | Mongolian input method based on touch input device |
| CN102646015A (en) * | 2012-02-01 | 2012-08-22 | 呼和浩特市元泰电子科技有限责任公司 | Mongolian virtual keyboard input method |
| CN103593061A (en) * | 2013-11-01 | 2014-02-19 | 梁金宝 | Intelligent Mongolian input method capable of being used for touch screen mobile phone |
-
2020
- 2020-05-18 CN CN202010418732.8A patent/CN111580685B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004206659A (en) * | 2002-11-07 | 2004-07-22 | Nippon Telegr & Teleph Corp <Ntt> | Reading information determination method, device, and program |
| CN1936791A (en) * | 2006-10-16 | 2007-03-28 | 孟和吉雅 | Mongol digital keyboard inputting method based on syllable |
| WO2008136647A1 (en) * | 2007-05-08 | 2008-11-13 | Young Jae Jung | A keypad array of mobile phone for inputting characters of russian language |
| CN102184031A (en) * | 2011-04-25 | 2011-09-14 | 内蒙古大学 | Mongolian input method based on touch input device |
| CN102646015A (en) * | 2012-02-01 | 2012-08-22 | 呼和浩特市元泰电子科技有限责任公司 | Mongolian virtual keyboard input method |
| CN103593061A (en) * | 2013-11-01 | 2014-02-19 | 梁金宝 | Intelligent Mongolian input method capable of being used for touch screen mobile phone |
Non-Patent Citations (1)
| Title |
|---|
| 白云莉;: "蒙古文整词输入法的设计与实现", 内蒙古农业大学学报(自然科学版) * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111580685B (en) | 2023-05-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110489760B (en) | Text automatic correction method and device based on deep neural network | |
| JP3531468B2 (en) | Document processing apparatus and method | |
| US7802184B1 (en) | Method and apparatus for processing text and character data | |
| CN105404621B (en) | A kind of method and system that Chinese character is read for blind person | |
| CN102122298A (en) | Method for matching Chinese similarity | |
| JP2005202917A (en) | System and method for eliminating ambiguity over phonetic input | |
| CN101133411A (en) | Fault-tolerant romanized input method for non-roman characters | |
| CN102214238A (en) | Device and method for matching similarity of Chinese words | |
| KR20230009564A (en) | Learning data correction method and apparatus thereof using ensemble score | |
| CN115587590A (en) | Training corpus construction method, translation model training method and translation method | |
| US10643028B1 (en) | Transliteration of text entry across scripts | |
| Uthayamoorthy et al. | Ddspell-a data driven spell checker and suggestion generator for the tamil language | |
| Roy et al. | Unsupervised context-sensitive bangla spelling correction with character n-gram | |
| CN113255331B (en) | Text error correction method, device and storage medium | |
| WO2014189400A1 (en) | A method for diacritisation of texts written in latin- or cyrillic-derived alphabets | |
| CN113673228A (en) | Text error correction method, text error correction device, computer storage medium and computer program product | |
| KR102129575B1 (en) | Word spelling correction system | |
| Ezeani et al. | Lexical disambiguation of Igbo using diacritic restoration | |
| Saloot et al. | Toward tweets normalization using maximum entropy | |
| CN111580685A (en) | Mongolian input method and input method system | |
| Mukund et al. | NE tagging for Urdu based on bootstrap POS learning | |
| CN113157852A (en) | Voice processing method, system, electronic equipment and storage medium | |
| JP3080066B2 (en) | Character recognition device, method and storage medium | |
| Manohar et al. | Spellchecker for Malayalam using finite state transition models | |
| CN113536776A (en) | Confusion statement generation method, terminal device and computer-readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |