CN114546127A - Novel keyboard design based on initial and final layouts - Google Patents

Novel keyboard design based on initial and final layouts Download PDF

Info

Publication number
CN114546127A
CN114546127A CN202210176856.9A CN202210176856A CN114546127A CN 114546127 A CN114546127 A CN 114546127A CN 202210176856 A CN202210176856 A CN 202210176856A CN 114546127 A CN114546127 A CN 114546127A
Authority
CN
China
Prior art keywords
initial
keyboard
final
characters
hand
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
Application number
CN202210176856.9A
Other languages
Chinese (zh)
Other versions
CN114546127B (en
Inventor
张昱宽
杨毅
苏昱恺
张宇泓
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Lanzhou University
Original Assignee
Lanzhou University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Lanzhou University filed Critical Lanzhou University
Priority to CN202210176856.9A priority Critical patent/CN114546127B/en
Publication of CN114546127A publication Critical patent/CN114546127A/en
Application granted granted Critical
Publication of CN114546127B publication Critical patent/CN114546127B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00Input 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
    • G06F3/01Input arrangements or combined input and output arrangements for interaction between user and computer
    • G06F3/02Input arrangements using manually operated switches, e.g. using keyboards or dials
    • G06F3/0202Constructional details or processes of manufacture of the input device
    • G06F3/0219Special purpose keyboards

Abstract

The invention discloses a novel keyboard design based on initial and final layouts in the technical field of computer equipment, which comprises a keyboard, wherein initial and final characters and punctuation characters are arranged on an input assembly of the keyboard; aiming at a character editing worker using double spelling to simplify and accelerate typing speed, the scheme is to judge the association degree of initial consonants and vowels according to the novel of every ten thousand characters, news and other materials and by utilizing a correlation matrix, analyze the arrangement sequence of the initial consonants and the vowels according to human engineering documents, manufacture an arrangement diagram of the initial consonants and the vowels, calculate the correlation between the initial consonants and the vowels, reasonably distribute the initial consonants and the vowels according to the working strength of each finger according to the balance principle of left-hand and right-hand alternation rate in human engineering, apply the layout of the vowel keyboard design to the existing keyboard, correspondingly change the key positions of the existing keyboard into the initial consonants and the vowels, thereby improving the Chinese input speed and reducing the code length error rate, the fatigue degree and the left-hand and right hand alternation rate.

Description

Novel keyboard design based on initial and final layouts
Technical Field
The invention relates to the technical field of computer equipment, in particular to a novel keyboard design based on initial and final layouts.
Background
At present, qwerty keyboard layout of a keyboard based on an English input method is designed for English input, but is not efficient for Chinese input, and has the main defects that the typing speed is low, and aiming at the characteristics of Chinese input, an initial consonant and vowel keyboard layout design scheme based on initial consonant and vowel relevance is designed, and a keyboard layout for efficient Chinese input is designed according to the scheme, so that a novel keyboard design based on initial consonant and vowel layout is provided.
Disclosure of Invention
The invention aims to provide a novel keyboard design based on initial and final layouts so as to solve the problems in the background technology.
In order to achieve the purpose, the invention provides the following technical scheme: the novel keyboard design based on the initial and final layout comprises a keyboard, wherein initial and final characters and punctuation characters are arranged on an input assembly of the keyboard;
the layout design steps of the initial consonant characters and the punctuation characters are as follows:
the method comprises the following steps: researching target user data;
step two: collecting initial consonant and vowel input data sets and analyzing an algorithm;
step three: cleaning initial consonant and vowel input data, and performing word segmentation operation to obtain a word sequence;
step four: extracting front and rear initial consonants contained in the words, calculating the occurrence frequency of each different ordered binary group, drawing a correlation matrix according to statistics, and visually analyzing the correlation between the initial consonants;
step five: according to the balance principle of left-hand and right-hand alternation rate in human engineering, the arrangement of the initials and the finals is reasonably distributed according to the working intensity;
step six: the key positions are correspondingly changed into initials and finals.
Preferably, the input component of the keyboard is a key cap.
Preferably, the target user in step one is a word editor using a binary syllabification to speed typing.
Preferably, the data collection in the second step includes capturing near ten million word materials of news, blogs and novels, counting the number of each initial consonant and vowel, and determining the association degree of the initial consonant and the vowel by using the correlation matrix.
Preferably, the cleaning of the initial and final input data in the third step includes screening out data which do not meet requirements, such as messy codes, wrongly written characters, English input and the like, and performing corresponding transcoding on the data which meet the conditions by using a python to read the pronunciation rule of the pinyin dictionary to obtain the required initial and final.
Compared with the prior art, the invention has the beneficial effects that: aiming at a character editing worker using double spelling to simplify and accelerate typing speed, the scheme is to judge the association degree of initial consonants and vowels according to the novel of every ten thousand characters, news and other materials and by utilizing a correlation matrix, analyze the arrangement sequence of the initial consonants and the vowels according to human engineering documents, manufacture an arrangement diagram of the initial consonants and the vowels, calculate the correlation between the initial consonants and the vowels, reasonably distribute the initial consonants and the vowels according to the working strength of each finger according to the balance principle of left-hand and right-hand alternation rate in human engineering, apply the layout of the vowel keyboard design to the existing keyboard, correspondingly change the key positions of the existing keyboard into the initial consonants and the vowels, thereby improving the Chinese input speed and reducing the code length error rate, the fatigue degree and the left-hand and right hand alternation rate.
Drawings
FIG. 1 is a schematic structural view of the present invention;
FIG. 2 is a schematic diagram of the arrangement of initials and finals according to the present invention;
FIG. 3 is a schematic illustration of statistical data for the investigation of the present invention;
FIG. 4 is a schematic illustration of statistical data for the investigation of the present invention;
FIG. 5 is a schematic illustration of statistical data for the investigation of the present invention;
FIG. 6 is a code diagram of a data crawling section of the present invention;
FIG. 7 is a schematic view of a data cleansing portion of the present invention;
FIG. 8 is a schematic view of a data cleansing portion of the present invention;
FIG. 9 is a graphical illustration of the initial data cleaning statistics of the present invention;
FIG. 10 is a diagram illustrating cleaning statistics of vowel data according to the present invention;
FIG. 11 is a schematic view of the present invention reviewing content of a document;
FIG. 12 is a schematic view of the present invention reviewing content of a document;
FIG. 13 is a code diagram of a portion of the data analysis of the present invention;
FIG. 14 is a diagram illustrating the statistics of the arrangement of initials and finals according to the present invention;
FIG. 15 is a diagram illustrating the statistics of the arrangement of initials and finals according to the present invention;
FIG. 16 is a schematic view of the present invention reviewing content of a document;
fig. 17 is a schematic view of the present invention for reviewing contents of documents.
In the figure: 1. a keyboard.
Detailed Description
Example one
Referring to fig. 1-17, the present invention provides a technical solution:
based on the novel keyboard design of initial and final layout, the appearance of the novel keyboard provided by the scheme is as shown in the attached figure 1 of the specification, and initial and final characters and punctuation characters are arranged on keycaps of the keyboard 1, so that the keyboard 1 is convenient for Chinese input;
according to the scheme, the common QWERT keyboard layout in the market is changed, English characters on the surfaces of the keycaps on the traditional keyboard are replaced by initial consonant characters and punctuation characters, and the keyboard design is more convenient for Chinese input.
The letter layout on the keyboard on the market at present is directed at an English input method, a layout specially designed for Chinese input does not appear at present, the project abandons a single letter spelling mode of English input, an initial consonant-vowel input mode is designed according to a Chinese spelling habit and the characteristic that Chinese input is mainly word, a complex vowel character is added, special symbols of English input are removed, the weight of each initial consonant is calculated by an algorithm, and the Chinese keyboard layout is designed by combining human engineering.
After research and research, most character editing workers using double spelling for simplifying and accelerating typing speed are found, and the keyboard can accelerate the typing speed of double spelling and improve the Chinese input speed.
Meanwhile, near ten million characters of three types of data of news, blogs and novels are captured, the number of each initial consonant and the final is counted, the correlation degree of the initial consonant and the final is judged by utilizing a correlation matrix, the arrangement sequence of the initial consonants and the final is analyzed according to human engineering documents, and the arrangement diagram of the initial consonants and the final is manufactured.
First, the questionnaire is analyzed for a specific user and a market, i.e., a group of people who need to use a large amount of chinese for typing (news editors, chinese novels authors) and the like, and the displayed results of the questionnaire are shown in fig. 3 to 5 of the specification. The questionnaire shows that 78.85% of users in the specific user oriented input, the existing keyboard with English layout has low efficiency for inputting Chinese characters, people are generally familiar with the layout of English keyboard but can not improve the efficiency better, and for this group we have carried out the second questionnaire issue to explore whether they are willing to accept the layout of Chinese keyboard, wherein 63.83% of users think that they are willing to accept the layout of Chinese keyboard as long as the efficiency of code word can be improved, wherein most of the word editors use double spelling, and we draw conclusions from the questionnaire: the project has good market prospect.
Then we continue to collect datasets (related works, scripts, etc.) for specific target users, crawl text data using the beautifuloup module, and crawl according to order or keyword information. By specifying the number of pages traversed, the contents of the specified website can be crawled and written locally.
Part of the code is shown in figure 6 in the specification.
And then cleaning the obtained data set, screening out data which do not meet requirements, such as messy codes, wrongly written characters, English input and the like, and performing corresponding transcoding on the data which meet the conditions by utilizing the pronunciation rule of a python reading pinyin dictionary to obtain the required initial consonants and vowels, wherein part of codes of the initial consonants and vowels are shown in the attached figures 7-8 of the following description.
The results are shown in FIGS. 9-10 of the specification.
Then, we consult the related literature (article number of the' English input keyboard layout modification): 1000-7024(2004)01-015304-04) and record that "the letter zone is left-right symmetrical so that only one side needs to be studied, the other side can correspondingly deduce 4 types of conditions that the right side is selected according to the movement of fingers and palms when clicking, the letter zone of the natural keyboard can be divided into some basic zones firstly, and 4 RMZs, RM3, RM4 and RMS, namely the keys initially placed by the fingers of the right hand when clicking are obtained for the 1 type of conditions (see the middle row light gray zone on the right side of FIG. 4 in FIG. 11 in the description); for the 2 nd case combined with the characteristics 35, it can be concluded that one key position RDZ of index finger retraction stroke and two key positions RU3 and RU4 of middle finger and ring finger extension stroke total 3 key positions, so that it can be concluded that the extended basic key position region is composed of 7 extended basic key positions (see the whole light gray area on the right side of figure 4 in figure 11 of the specification) including 4 basic key positions; for the 4 th case, the corresponding key position area which is most difficult to use can be obtained (see the upper left corner dark gray key position on the right side of the figure 3 in the attached figure 11 of the specification); finally, the general key position area corresponding to the 3 RD type condition, i.e. the area composed of the other 5 key positions RUZRMIRDIRD3 and RD4 except the expanded basic key position area and the most difficult key position area, is obtained, for the letter area of the general keyboard, because the left side of the letter area does not conform to the natural angle of the left hand when the user clicks, the left side of the letter area is not in bilateral symmetry, so that the adjustment is needed to be made according to the using difficulty and the ease sequence of the key positions of the natural keyboard, for example, for the expanded basic key position area on the left side of the letter area, because the left hand and the index finger retract to hit and the key position which does not pull the wrist does not exist, one expanded basic key position is reduced (see all light gray areas on the left side of figure 6 in figure 11 in the description), for the numbers of the expanded basic key position area of the natural keyboard, the order of the index finger and the little finger responsible for hitting is increased sequentially, which is because the key positions of the non-basic key position area of the characteristic 4 are all larger than the corresponding key positions (correspondingly, respectively, the same finger is responsible for hitting otherwise), is because the condition 2 It should be noted that the most important key position number for the little finger to hit is because the difficulty level of using the key position in the most difficult key position area and the normal key position area corresponding to the feature 6 can be similar to the last, and the difficulty level of using the key position on the left side of the natural keyboard can be obtained according to the features 1 and 2, which can be referred to all the numbers in the figure 11 of the description and figure 6 of the figure 4 of the figure size of the general keyboard letter area on the left side of the figure 11 of the description.
Based on the difficulty degree of using each key in the key area in the document, the initial consonant obtained after the analysis is placed in an easy place in the key position, and most of the final consonants only need to be complemented by pressing tab keys based on the word input of the project.
In the key position design arrangement, the load born by the flexibility degree of each finger in human engineering is also considered, the reference document is 'exploration about the keyboard letter layout of the Chinese phonetic input method' chapter number: 1003-; according to engineering psychology experimental data, the interval of the motion of knocking the keyboard by the same finger is 0.09s on average, the interval of the knocking motion between different fingers of the same hand is 0.03s on average, the interval of the knocking motion between the fingers of different hands is 0.02s on average, the efficiency of alternatively knocking the keyboard by the left hand and the right hand is higher than the efficiency of continuously knocking the keyboard by a single hand, and the fingers are less fatigued under the condition, so that the knocking motion is performed alternately in the left hand and the right hand as much as possible, and the recorded data are shown in the attached figure 12 of the specification.
Secondly, when considering common initial consonant statistics, in order to discharge more initial consonants of Chinese characters to a more suitable position, the value of the alternation rate is required to be as close to 1 as possible, and the reference is 'exploration about the keyboard letter layout of the Chinese pinyin input method' chapter number: 1003-0077(2010)06-0108-06 ', wherein the description is that' a left key region is an A region, a right key region is a B region, and the pinyin of a Chinese character is a1a2 … ai … an, wherein ai ∈ { a, B, c, …, z }, the pinyin length a1a2 … ai … an <7, i ═ 1, 2, …, N, N ∈ N +, if ai appears in the A region and ai +1 appears in the B region, a certain character is called that the left hand and the right hand are alternated, and the ratio of the number p of Chinese characters which are alternated by the left hand and the right hand to the total number q of Chinese characters is called as the alternation rate. Here, we use the alternation rate for reference, and consider that the initial combination under the condition of left-hand and right-hand matching can drive more words, i.e. more Chinese characters, so that the value of the alternation rate approaches to 1 as much as possible, and we analyze a large number of data sets through python, and part of codes of the data sets are shown in the attached figure 13 of the specification.
And (5) counting the correlation of the parents of all the two-word words, and constructing a correlation matrix. And the keyboard layout is preliminarily designed according to the statistical result, the display result is shown in the attached figures 14-15 of the specification, and the darker areas in the figures are the combinations of the initial consonants, so that more words can appear in the combinations of the initial consonants, and the initial consonants can be placed in more reasonable places.
Continuing, we have further studied human engineering, and the reference is 'exploration on the keyboard letter layout of the Chinese pinyin input method' chapter number: 1003-. "it is reasonable to have a left keypad larger than a right keypad in the workload, but not much more than necessary, as shown by the graph data; it is reasonable in workload that the middle row > the upper row > the lower row. We also use this as one of the important factors of the layout in the keyboard layout.
Therefore, the arrangement of the initial consonant and vowel characters in the attached figure 1 of the specification is designed at present.
In conclusion, the design idea of the scheme is as follows:
firstly, determining a specific user group, collecting corpus data on regular websites such as a national statistical network and CNKI (CNKI), taking the corpus data as a data set for empirical statistical analysis, respectively counting word frequencies of two-word words and multi-word words through technical means such as data cleaning and word segmentation, constructing a dictionary from Chinese characters to pinyin, and mapping the Chinese characters to the pinyin;
analyzing the correlation between the initials and the finals in the vocabulary by utilizing the principle of statistics, and determining the importance of the corresponding key positions according to the strength and the occurrence frequency of the dependency relationship;
thirdly, the keyboard layout based on the initial consonant and the vowel key positions, which has higher alternation rate, can enable the fingers to be less fatigued by comprehensively designing a theory by combining the difficulty degree of using each key position in the traditional keyboard layout, the flexibility degree of each finger in human engineering and the corresponding load capacity;
fourthly, analysis algorithm: text data are collected for a class of people needing layout design and are mapped to corresponding pinyin sequences and consonant and vowel sequences. And then converting the pinyin sequence into a directed weight graph by using a TextRank algorithm. The important components in the text are sorted by using a voting mechanism, and the key words can be sorted only by using the information of the current document. The required key words are not extracted finally, but undirected weighted graphs learned by the model in the iterative training process are extracted and used as references of keyboard layout;
and fifthly, in concrete implementation, word segmentation and part-of-speech tagging are carried out on each original text data, stop words are filtered, transition to a pinyin sequence is completed, and sequencing based on correlation degree between initial consonants and vowels in pinyin is completed. The input of the sequence further refines the analysis of the original sentence level of the TextRank, and considers the co-occurrence degree of the initials and the finals by taking the combination of n continuous initials and finals in the pinyin sequence as metadata. Firstly, inputting a pinyin sequence which is mapped as a model, carrying out sequence annotation, and constructing an undirected graph G (V, E) related to initials and finals, wherein V is a node set and consists of all initials and finals, and E is an edge set and represents the correlation degree between connected nodes. And then, iteratively calculating an edge between two points by adopting a co-occurrence relationship (co-occurrence), wherein a relation necessarily exists between any two nodes, and the strength of the relation between the nodes is learned by inputting a pinyin sequence through the model. The setting of the collinear window size K is to be evaluated experimentally as a hyper-parameter. And (4) iteratively propagating the weight of each node and the weight of each edge according to a formula. On the other hand, the relevance calculation at the sentence level is separated, and the relevance of different initial consonants is directly calculated on the global context;
and sixthly, in implementation, the vocabulary sequence is obtained through data cleaning and word segmentation operation. And then extracting the front initial consonant and the rear initial consonant contained in the words, calculating the occurrence frequency of each different ordered binary group, drawing a correlation matrix according to statistics, and visually analyzing the correlation between the initial consonants.
And seventhly, a basic use rule of the input method is that after the correlation between the initials and the finals is calculated, according to a balance principle of left-hand and right-hand alternation rates in human engineering, a user hopes that the initials are input by the left hand of the user and then the finals are input by the right hand, or the finals are input by the left hand of the user after the initials are input by the right hand, according to the balance principle of left-hand and right-hand workload, the left-hand and right-hand workload is reasonably arranged in a designed way, so that the left-hand and right-hand workload is approximately the same, and the fingers are reasonably distributed according to the working intensity. Meanwhile, reasonable distribution is carried out on the layout according to the working strength of each finger.
Eighthly, letter key position arrangement design idea: the input of the Chinese character is divided into an initial consonant and a final sound, and the key positions are correspondingly changed into the initial consonant and the final sound. The whole initial consonant is positioned at the upper part of the keyboard. The consonants are directly input, and the vowels are input in a mode of complementing by using a complementing key.
Based on the layout design idea, the keyboard layout design mode is compared with a full spelling mode and a double spelling mode:
1. contrast double spelling
The specific vowel position mapping in the double spelling does not need to be memorized, and the vowel position mapping is visually represented by different key positions in the keyboard layout;
2. contrast full spelling
The designed keyboard based on the initial and final layout is superior to full spelling in the aspects of code length error rate (the code length is the number of times of pressing keys required for inputting a character, for example, the zhang full spelling code length is 5, while the novel keyboard only needs zh and ang, the code length is 2), fatigue and left-right hand alternation rate. Through logic analysis, the main reason for the difference is considered to be that the average code length is greatly reduced, the same content is input, the number of times of key pressing of the full spelling is more than that of the mode based on the initial consonants and vowels, the full spelling is slower to a certain extent on the premise of certain key pressing speed, the number of times of input of the full spelling is more, and therefore the possibility that errors need to be modified is higher.

Claims (5)

1. Novel keyboard design based on initial consonant and final overall arrangement, including keyboard (1), its characterized in that: the input component of the keyboard (1) is provided with initial consonant characters and punctuation characters;
the layout design steps of the initial consonant characters and the punctuation characters are as follows:
the method comprises the following steps: researching target user data;
step two: collecting initial consonant and vowel input data sets and analyzing an algorithm;
step three: cleaning initial consonant and vowel input data, and performing word segmentation operation to obtain a word sequence;
step four: extracting front and rear initial consonants contained in the words, calculating the occurrence frequency of each different ordered binary group, drawing a correlation matrix according to statistics, and visually analyzing the correlation between the initial consonants;
step five: according to the balance principle of left-hand and right-hand alternation rate in ergonomics, the arrangement of the initials and finals is reasonably distributed according to the working intensity;
step six: the key positions are correspondingly changed into initials and finals.
2. The novel keyboard design based on initial and final layouts of claim 1, wherein: the input component of the keyboard (1) is a keycap.
3. The novel keyboard design based on initial and final layouts of claim 1, wherein: the target user in step one is a word editor who uses double spelling to speed up typing speed.
4. The novel keyboard design based on initial and final layouts of claim 1, wherein: and the data collection in the second step comprises the steps of grabbing near ten million word materials of three types of data of news, blogs and novels, counting the number of each initial consonant and vowel, and judging the association degree of the initial consonant and the vowel by utilizing a correlation matrix.
5. The novel keyboard design based on initial and final layouts of claim 1, wherein: and in the third step, cleaning the initial and final input data, namely screening out data which do not meet the requirements, such as messy codes, wrongly written characters, English input and the like, and performing corresponding transcoding on the data meeting the conditions by utilizing the python to read the pronunciation rule of the pinyin dictionary to obtain the required initial and final.
CN202210176856.9A 2022-02-25 2022-02-25 Keyboard design method based on initial consonant and vowel layout Active CN114546127B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210176856.9A CN114546127B (en) 2022-02-25 2022-02-25 Keyboard design method based on initial consonant and vowel layout

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210176856.9A CN114546127B (en) 2022-02-25 2022-02-25 Keyboard design method based on initial consonant and vowel layout

Publications (2)

Publication Number Publication Date
CN114546127A true CN114546127A (en) 2022-05-27
CN114546127B CN114546127B (en) 2023-11-24

Family

ID=81679337

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210176856.9A Active CN114546127B (en) 2022-02-25 2022-02-25 Keyboard design method based on initial consonant and vowel layout

Country Status (1)

Country Link
CN (1) CN114546127B (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1556457A (en) * 2004-01-05 2004-12-22 郑 方 Chinese whole sentence input method based on key selection double spelling and its keyboard arrangement
CN101174182A (en) * 2006-11-02 2008-05-07 尚晓 Chinese character input method
CN101349946A (en) * 2007-07-20 2009-01-21 无锡职业技术学院 Digital shape-pronunciation code Chinese input method and keyboard
CN104765468A (en) * 2014-01-05 2015-07-08 张刚 Syllable initial and syllable rime double-keyboard sliding input method

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1556457A (en) * 2004-01-05 2004-12-22 郑 方 Chinese whole sentence input method based on key selection double spelling and its keyboard arrangement
CN101174182A (en) * 2006-11-02 2008-05-07 尚晓 Chinese character input method
CN101349946A (en) * 2007-07-20 2009-01-21 无锡职业技术学院 Digital shape-pronunciation code Chinese input method and keyboard
CN104765468A (en) * 2014-01-05 2015-07-08 张刚 Syllable initial and syllable rime double-keyboard sliding input method

Also Published As

Publication number Publication date
CN114546127B (en) 2023-11-24

Similar Documents

Publication Publication Date Title
Abu Nada et al. Arabic text summarization using arabert model using extractive text summarization approach
Ali et al. Hate speech detection on Twitter using transfer learning
Elbarougy et al. Extractive Arabic text summarization using modified PageRank algorithm
US9519634B2 (en) Systems and methods for determining lexical associations among words in a corpus
Weiss et al. Text mining: predictive methods for analyzing unstructured information
Zhang et al. Subword-augmented embedding for cloze reading comprehension
Rani et al. Performance evaluation of text-mining models with Hindi stopwords lists
Yadav et al. Extractive Text Summarization Using Recent Approaches: A Survey.
Malik et al. Text mining life cycle for a spatial reading of Viet Thanh Nguyen's The Refugees (2017)
Payak et al. Automatic text summarization and keyword extraction using natural language processing
Sanchez-Gomez et al. Sentiment-oriented query-focused text summarization addressed with a multi-objective optimization approach
Patel et al. Approaches of anonymisation of an SMS corpus
Akther et al. Compilation, analysis and application of a comprehensive Bangla Corpus KUMono
Yang et al. Conflibert-spanish: A pre-trained spanish language model for political conflict and violence
CN114546127B (en) Keyboard design method based on initial consonant and vowel layout
Jindal et al. U-struct: A framework for conversion of unstructured text documents into structured form
Li et al. A phrase topic model for large-scale corpus
Mamidala A heuristic approach for telugu text summarization with improved sentence ranking
Mahmoud et al. Arabic semantic textual similarity identification based on convolutional gated recurrent units
Hosseinabadi et al. ISSE: a new iterative sentence scoring and extraction scheme for automatic text summarization
Maria et al. A new model for Arabic multi-document text summarization
BAZRFKAN et al. Using machine learning methods to summarize persian texts
Patra et al. A novel word clustering and cluster merging technique for named entity recognition
Salama et al. The integration of a newly defined N-gram concept and vector space model for documents ranking
CN112949287B (en) Hot word mining method, system, computer equipment and 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