CN113807105A - French geographical name machine translation method - Google Patents
French geographical name machine translation method Download PDFInfo
- Publication number
- CN113807105A CN113807105A CN202111122788.XA CN202111122788A CN113807105A CN 113807105 A CN113807105 A CN 113807105A CN 202111122788 A CN202111122788 A CN 202111122788A CN 113807105 A CN113807105 A CN 113807105A
- Authority
- CN
- China
- Prior art keywords
- name
- french
- place
- place name
- preprocessed
- 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
- G06F40/00—Handling natural language data
- G06F40/40—Processing or translation of natural language
- G06F40/42—Data-driven translation
- G06F40/44—Statistical methods, e.g. probability models
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/40—Processing or translation of natural language
- G06F40/42—Data-driven translation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/40—Processing or translation of natural language
- G06F40/42—Data-driven translation
- G06F40/47—Machine-assisted translation, e.g. using translation memory
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/40—Processing or translation of natural language
- G06F40/58—Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L13/00—Speech synthesis; Text to speech systems
- G10L13/08—Text analysis or generation of parameters for speech synthesis out of text, e.g. grapheme to phoneme translation, prosody generation or stress or intonation determination
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/40—Processing or translation of natural language
- G06F40/53—Processing of non-Latin text
-
- 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
Abstract
The invention discloses a French geographical name machine translation method, which comprises the following steps: firstly, distinguishing the preprocessed French-geographical name phrases to obtain a geographical name full name part and a geographical name proper name part; secondly, translating the part of the place name proper name according to letter combinations in a French-Chinese transliteration table to obtain a proper name transliteration result; then, translating the place name part according to the geographic entity type pointed by the French full name to obtain a full name transliteration result; and finally integrating the special name transliteration result and the full name transliteration result to obtain a place name translation result. The technical scheme disclosed by the invention realizes machine translation, reduces the manpower consumption during place name generation and improves the efficiency of translating French place names.
Description
Technical Field
The invention relates to the technical field of place name translation, in particular to a French place name machine translation method.
Background
Place name translation refers to the translation of an expression of a geographic entity in one language into an expression in another language. Generally speaking, place names are divided into a place name part and a place name part, and the place name part is a general word for summarizing the commonality (category) of certain places and plays a qualitative role; the place name part is a special word which refers to a certain geographic entity and is used for distinguishing similar ground objects, and plays a role in positioning. Automatic place name translation, or machine place name translation, is part of the translation of named entities in machine translation. However, this part is the most difficult of all named entity translations. First, the composition of place names is complex, and the composition of place names at different scales is very different. Secondly, the translation of place names needs to consider two parts of common names and special names, namely transliteration and transliteration, so that more universal machine translations cannot independently solve the translation problem of place names, and the translation of French place names is mainly carried out manually at present, so that the problem of low efficiency exists.
Disclosure of Invention
The invention aims to provide a French geographical name machine translation method to improve the translation efficiency of French geographical names.
In order to achieve the above object, the present invention provides a french place name machine translation method, including:
acquiring a French-place name phrase to be translated;
preprocessing the French geographical name phrase;
distinguishing based on the preprocessed French-place name phrases to obtain a place name common part and a place name proper part;
translating the part of the place name proper name according to letter combinations in a French-Chinese transliteration table to obtain a proper name transliteration result;
translating the place name part according to the geographic entity type pointed by the French full name to obtain a full name transliteration result;
and integrating the special name transliteration result and the common name transliteration result to obtain a place name translation result.
Optionally, the distinguishing based on the preprocessed french-language place name phrases to obtain a place name common part and a place name proper part specifically includes:
determining a place name full name template based on a preprocessed French place name phrase stored in a place name corpus;
determining all the common name structure decomposition schemes according to the place name common name templates;
calculating the logarithmic frequency corresponding to each place name common name template;
summing the logarithmic frequencies in the same wildcard structure decomposition scheme to obtain a logarithmic frequency sum corresponding to each wildcard structure decomposition scheme;
taking the wildname structure decomposition scheme with the maximum sum of the logarithmic frequencies as the place name structure tree;
using sub-leaf nodes of the place name structure tree as the place name proper part; and taking the non-sub-leaf node of the place name structure tree as the place name common name part.
Optionally, the determining a place name full name template based on the preprocessed french place name phrases stored in the place name corpus specifically includes:
by usingCalculating mutual information of any ordered word pair in the place name corpus; wherein, PaRepresenting the frequency, P, of the occurrence of the preprocessed French-language place-name phrase a in the place-name corpusbRepresenting the frequency, P, of the occurrence of the preprocessed French-language place-name phrase b in the place-name corpusabDenotes the co-occurrence frequency, MI, between the preprocessed French-name phrases a and babRepresenting mutual information of the ordered word pair (a, b); the preprocessed French-language place-name phrases a and the preprocessed French-language place-name phrases b form an ordered word pair (a, b);
storing the ordered word pairs with the co-occurrence frequency larger than a first set value and the mutual information larger than a second set value in the place name corpus into an ordered word pair library;
traversing all sentences, and taking French geographical name phrases which form preprocessed in each sentence as points on the directed acyclic graph; when two preprocessed French-language place name word groups in the sentence belong to the ordered word pairs in the ordered word pair library, connecting two points on the directed acyclic graph to form a line and drawing the line into a directed edge;
finding out all paths on the directed acyclic graph, and generating a candidate place name template for each path according to the preprocessed French place name phrases corresponding to the access nodes; the path is composed of a plurality of directed edges;
and counting the frequency of each candidate place name template, and taking the candidate place name template with the frequency greater than a set frequency threshold value as a place name common name template.
Optionally, the translating the part of the place name proper name according to a letter combination in a french-chinese transliteration table to obtain a proper name transliteration result specifically includes:
carrying out unsupervised learning on the word letters by taking the minimum entropy as a principle to obtain letter combination distribution;
segmenting and combining the letters in the place name part by adopting a shortest path method word segmentation method to obtain a plurality of letter combinations;
calculating the average entropy values of different letter combinations according to the letter combination distribution;
selecting the letter combination with the minimum entropy value as the optimal letter combination;
and the optimal letter combination is translated into the Chinese character according to the French-Chinese transliteration table, so that a proper name transliteration result is obtained.
Optionally, the translating the place name part according to the geographic entity category indicated by the french full name to obtain the full name transliteration result specifically includes:
translating and analyzing the place name common name part by using a French-Chinese dictionary and the place name common name template to obtain a place name hierarchical grammar structure;
and converting the French geographical name elements in the geographical name hierarchical grammar structure into Chinese geographical name elements layer by layer according to a bottom-up principle to obtain a transliteration result of the full name.
The invention discloses a French geographical name machine translation method, which comprises the following steps: firstly, distinguishing the preprocessed French-geographical name phrases to obtain a geographical name full name part and a geographical name proper name part; secondly, translating the part of the place name proper name according to letter combinations in a French-Chinese transliteration table to obtain a proper name transliteration result; then, translating the place name part according to the geographic entity type pointed by the French full name to obtain a full name transliteration result; and finally integrating the special name transliteration result and the full name transliteration result to obtain a place name translation result. The technical scheme disclosed by the invention realizes machine translation, reduces the manpower consumption during place name generation and improves the efficiency of translating French place names.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without inventive exercise.
FIG. 1 is a flow chart of a French geographical name machine translation method of the present invention;
FIG. 2 is a detailed flow chart for distinguishing a place name part and a place name part according to the present invention;
FIG. 3 is a detailed flowchart of determining a place name full name template based on a preprocessed French place name phrase stored in a place name corpus according to the present invention;
FIG. 4 is a detailed flow chart of the proper name transliteration of the present invention;
FIG. 5 is a detailed flow chart of the present invention for transliteration of a common name.
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 invention aims to provide a French geographical name machine translation method to improve the translation efficiency of French geographical names.
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
As shown in fig. 1, the present invention discloses a french place name machine translation method, which is characterized in that the method comprises:
step S1: acquiring a French-place name phrase to be translated; and the phrase forming the French place name is called the French place name phrase.
Step S2: and preprocessing the French geographical name phrase.
Step S3: and distinguishing based on the preprocessed French-place name phrases to obtain a place name common name part and a place name proper name part.
Step S4: and translating the part of the place name proper name according to letter combinations in a French-Chinese transliteration table to obtain a proper name transliteration result.
Step S5: and translating the place name part according to the geographic entity type pointed by the French full name to obtain a full name transliteration result.
Step S6: and integrating the special name transliteration result and the common name transliteration result to obtain a place name translation result.
The individual steps are discussed in detail below:
step S2: preprocessing the French geographical name phrase; the articles, the symbols, the illegal characters and the like in the French-language place name phrase are not beneficial to place name machine translation, so that the special symbols such as the articles, the illegal letters and the punctuation marks which are not beneficial to place name machine translation are removed before the division of the common names and the proper names, and the accuracy of the subsequent division of the common names and the proper names is further improved.
As shown in fig. 2 to 3, step S3: distinguishing based on the preprocessed French geographical name phrases to obtain a geographical name common part and a geographical name proper part, and specifically comprising the following steps:
step S31: the method comprises the following steps of determining a place name common name template based on a preprocessed French place name phrase stored in a place name corpus, and specifically comprises the following steps:
step S311: calculating mutual information of any ordered word pair in the place name corpus, wherein the specific formula is as follows:wherein, PaRepresenting the frequency, P, of the occurrence of the preprocessed French-language place-name phrase a in the place-name corpusbRepresenting the frequency, P, of the occurrence of the preprocessed French-language place-name phrase b in the place-name corpusabDenotes the co-occurrence frequency, MI, between the preprocessed French-name phrases a and babRepresenting mutual information of the ordered word pair (a, b); and the preprocessed French geographical name phrase a and the preprocessed French geographical name phrase b form an ordered word pair (a, b).
Step S312: co-occurrence frequency P in the place name corpusabGreater than a first set value T1And mutual information MIabIs greater than a second set value T2The ordered word pairs are stored in an ordered word pair bank G.
Step S313: traversing all sentences, and taking French geographical name phrases which form preprocessed in each sentence as points on the directed acyclic graph; when two preprocessed French-place name phrases in the sentence belong to the ordered word pair in the ordered word pair library, two points are connected into a line on the directed acyclic graph, and a directed edge ' a ' -b ' is drawn.
Step S314: finding out all paths on the directed acyclic graph, and generating a candidate place name template for each path according to the preprocessed French place name phrases corresponding to the access nodes; the path is composed of a plurality of directed edges. In this embodiment, if a neighbor node is crossed, a placeholder is inserted.
Step S315: and counting the frequency of each candidate place name template, and taking the candidate place name template with the frequency greater than a set frequency threshold value as a place name common name template.
Step S32: and determining all the common name structure decomposition schemes according to the place name common name templates.
Step S33: and calculating the logarithmic frequency corresponding to each place name common name template.
Step S34: and summing all the logarithmic frequencies in the same wildcard structure decomposition scheme to obtain the logarithmic frequency sum corresponding to each wildcard structure decomposition scheme.
Step S35: and taking the wildname structure decomposition scheme with the maximum sum of the logarithmic frequencies as the place name structure tree.
Step S36: using sub-leaf nodes of the place name structure tree as the place name proper part; and taking the non-sub-leaf node of the place name structure tree as the place name common name part.
Specifically, a given piece of input preprocessed french place name phrases is subjected to structural decomposition by using the place name full-name template obtained in step S31, so as to generate a place name structure tree. In order to realize the structural decomposition of the preprocessed French-name phrases, the projection (tentative) hypothesis of syntactic analysis is used for reference. The present invention proposes the following assumptions of structural decomposition:
1. the preprocessed French-language place name phrase is composed of a plurality of place name full name templates which are not crossed with each other;
2. the placeholder part of the place name template is also a place name wildname template;
3. each individual preprocessed french place name phrase can be regarded as a special place name full name template.
Based on the above assumptions, the invention provides a place name phrase structure decomposition method: a series of place name common name templates are found to cover each word in the place name phrase without overlapping, missing or crossing, so that the sum of the probability logarithms of the place name common name templates is maximum. Specifically, the method can be divided into two steps:
1. scanning all possible place name template conditions in the place name entries;
2. traversing all legal structure decomposition schemes according to all possible place name common name templates, and calculating the logarithmic frequency (namely taking the logarithm of the frequency) of each structure decomposition scheme: and calculating the sum of the probability logarithms of all place name common name templates in the decomposition scheme to obtain a logarithmic frequency value corresponding to each common name structure decomposition scheme, and selecting the structure decomposition scheme with the maximum logarithmic frequency as a place name structure tree.
In the place name structure tree, non-sub-leaf nodes are regarded as the universal place nouns and sub-leaf nodes are regarded as candidate proper place nouns on the basis of the assumption of structure decomposition, so that place name universal place name recognition is achieved in a classification mode.
As shown in fig. 4, step S4: translating the part of the place name proper name according to letter combinations in a French-Chinese transliteration table to obtain a proper name transliteration result, which specifically comprises the following steps:
step S41: and carrying out unsupervised learning on the word letters by taking the minimum entropy as a principle to obtain letter combination distribution.
Step S42: segmenting and combining the letters in the place name part by adopting a shortest path method word segmentation method to obtain a plurality of letter combinations; the letter combination division needs to divide letter combinations as little as possible so as to meet the requirement of transliteration to be as short as possible.
Step S43: and calculating the average entropy values of different letter combinations according to the letter combination distribution.
Entropy is a measure of the amount of information contained in a variable, and for a random variable x, whose probability density function (distribution) is P, the entropy of the random variable is E ═ P (x) logp (x), and in the case of discretization, may be denoted E ═ P (x) logp (x). The principle of minimum entropy is to minimize the entropy E by modifying the probability density function (distribution) so as to minimize the redundant information contained in the variable.
The invention firstly defines an average letter entropy E ═ Sigmax∈ΓP (x) logp (x), where p (x) represents the probability distribution of letter combination x appearing in the corpus, and Γ represents the set of letter combinations. Thus, calculating the average entropy values for different letter combinations can be expressed as:
wherein P (x) represents the probability distribution of letter combination x appearing in the corpus, lxRepresents the length of the letter combination (consisting of several letters), and theta representsThe letter combinations form a set, and E represents the average entropy values of different letter combinations.
Step S44: and selecting the letter combination with the minimum entropy value as the optimal letter combination.
Step S45: and the optimal letter combination is translated into the Chinese character according to the French-Chinese transliteration table, so that a proper name transliteration result is obtained. At present, the rule mainly uses a French-Chinese transliteration table formulated by national standard (foreign language place name Chinese character translation guide (GB/T17693.3-1999)).
As shown in fig. 5, step S5: translating the place name part according to the geographic entity type pointed by the French full name to obtain a full name transliteration result, which specifically comprises the following steps:
step S51: and translating and analyzing the place name part by using a French-Chinese dictionary and the place name template to obtain a place name hierarchical grammar structure.
Step S52: and converting the French geographical name elements in the geographical name hierarchical grammar structure into Chinese geographical name elements layer by layer according to a bottom-up principle to obtain a transliteration result of the full name.
The principles and embodiments of the present invention have been described herein using specific examples, which are provided only to help understand the method and the core concept of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, the specific embodiments and the application range may be changed. In view of the above, the present disclosure should not be construed as limiting the invention.
Claims (5)
1. A french place name machine translation method, the method comprising:
acquiring a French-place name phrase to be translated;
preprocessing the French geographical name phrase;
distinguishing based on the preprocessed French-place name phrases to obtain a place name common part and a place name proper part;
translating the part of the place name proper name according to letter combinations in a French-Chinese transliteration table to obtain a proper name transliteration result;
translating the place name part according to the geographic entity type pointed by the French full name to obtain a full name transliteration result;
and integrating the special name transliteration result and the common name transliteration result to obtain a place name translation result.
2. The french place name machine translation method according to claim 1, wherein the distinguishing based on the preprocessed french place name phrases obtains a place name common part and a place name proper part, and specifically comprises:
determining a place name full name template based on a preprocessed French place name phrase stored in a place name corpus;
determining all the common name structure decomposition schemes according to the place name common name templates;
calculating the logarithmic frequency corresponding to each place name common name template;
summing the logarithmic frequencies in the same wildcard structure decomposition scheme to obtain a logarithmic frequency sum corresponding to each wildcard structure decomposition scheme;
taking the wildname structure decomposition scheme with the maximum sum of the logarithmic frequencies as the place name structure tree;
using sub-leaf nodes of the place name structure tree as the place name proper part; and taking the non-sub-leaf node of the place name structure tree as the place name common name part.
3. The french place name machine translation method according to claim 2, wherein the determining of the place name full name template based on the preprocessed french place name phrases stored in the place name corpus specifically comprises:
by usingCalculating mutual information of any ordered word pair in the place name corpus; wherein, PaRepresenting the frequency, P, of the occurrence of the preprocessed French-language place-name phrase a in the place-name corpusbRepresentation preprocessingThe frequency, P, of occurrence of the subsequent French-language place-name phrase b in the place-name corpusabDenotes the co-occurrence frequency, MI, between the preprocessed French-name phrases a and babRepresenting mutual information of the ordered word pair (a, b); the preprocessed French-language place-name phrases a and the preprocessed French-language place-name phrases b form an ordered word pair (a, b);
storing the ordered word pairs with the co-occurrence frequency larger than a first set value and the mutual information larger than a second set value in the place name corpus into an ordered word pair library;
traversing all sentences, and taking French geographical name phrases which form preprocessed in each sentence as points on the directed acyclic graph; when two preprocessed French-language place name word groups in the sentence belong to the ordered word pairs in the ordered word pair library, connecting two points on the directed acyclic graph to form a line and drawing the line into a directed edge;
finding out all paths on the directed acyclic graph, and generating a candidate place name template for each path according to the preprocessed French place name phrases corresponding to the access nodes; the path is composed of a plurality of directed edges;
and counting the frequency of each candidate place name template, and taking the candidate place name template with the frequency greater than a set frequency threshold value as a place name common name template.
4. The french geographical name machine translation method of claim 1, wherein the translating the geographical name part according to letter combinations in a french-chinese transliteration table to obtain a transliteration result specifically comprises:
carrying out unsupervised learning on the word letters by taking the minimum entropy as a principle to obtain letter combination distribution;
segmenting and combining the letters in the place name part by adopting a shortest path method word segmentation method to obtain a plurality of letter combinations;
calculating the average entropy values of different letter combinations according to the letter combination distribution;
selecting the letter combination with the minimum entropy value as the optimal letter combination;
and the optimal letter combination is translated into the Chinese character according to the French-Chinese transliteration table, so that a proper name transliteration result is obtained.
5. The french place name machine translation method according to claim 2, wherein translating the place name part according to the geographic entity category to which the french place name part refers to obtain a transliteration result specifically comprises:
translating and analyzing the place name common name part by using a French-Chinese dictionary and the place name common name template to obtain a place name hierarchical grammar structure;
and converting the French geographical name elements in the geographical name hierarchical grammar structure into Chinese geographical name elements layer by layer according to a bottom-up principle to obtain a transliteration result of the full name.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
AU2021104429 | 2021-07-22 | ||
AU2021104429A AU2021104429A4 (en) | 2021-07-22 | 2021-07-22 | Machine Translation Method for French Geographical Names |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113807105A true CN113807105A (en) | 2021-12-17 |
CN113807105B CN113807105B (en) | 2023-07-21 |
Family
ID=77666647
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111122788.XA Active CN113807105B (en) | 2021-07-22 | 2021-09-24 | French place name machine translation method |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN113807105B (en) |
AU (1) | AU2021104429A4 (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116050420A (en) * | 2022-11-12 | 2023-05-02 | 武汉大学 | Chinese and French voice semantic recognition method and device based on preposition sentence |
CN117592462A (en) * | 2024-01-18 | 2024-02-23 | 航天宏图信息技术股份有限公司 | Correlation processing method and device for open source place name data based on place group |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2006252290A (en) * | 2005-03-11 | 2006-09-21 | Advanced Telecommunication Research Institute International | Machine translation device and computer program |
CN102253930A (en) * | 2010-05-18 | 2011-11-23 | 腾讯科技(深圳)有限公司 | Method and device for translating text |
CN109829173A (en) * | 2019-01-21 | 2019-05-31 | 中国测绘科学研究院 | A kind of English place name interpretation method and device |
CN111709238A (en) * | 2020-06-04 | 2020-09-25 | 中国地质大学(北京) | Web page geoscience correlation calculation method based on geoscience expert knowledge |
CN112084796A (en) * | 2020-09-15 | 2020-12-15 | 南京文图景信息科技有限公司 | Multi-language place name root Chinese translation method based on Transformer deep learning model |
CN112905595A (en) * | 2021-03-05 | 2021-06-04 | 腾讯科技(深圳)有限公司 | Data query method and device and computer readable storage medium |
CN112966068A (en) * | 2020-11-09 | 2021-06-15 | 袭明科技(广东)有限公司 | Resume identification method and device based on webpage information |
-
2021
- 2021-07-22 AU AU2021104429A patent/AU2021104429A4/en not_active Ceased
- 2021-09-24 CN CN202111122788.XA patent/CN113807105B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2006252290A (en) * | 2005-03-11 | 2006-09-21 | Advanced Telecommunication Research Institute International | Machine translation device and computer program |
CN102253930A (en) * | 2010-05-18 | 2011-11-23 | 腾讯科技(深圳)有限公司 | Method and device for translating text |
CN109829173A (en) * | 2019-01-21 | 2019-05-31 | 中国测绘科学研究院 | A kind of English place name interpretation method and device |
CN111709238A (en) * | 2020-06-04 | 2020-09-25 | 中国地质大学(北京) | Web page geoscience correlation calculation method based on geoscience expert knowledge |
CN112084796A (en) * | 2020-09-15 | 2020-12-15 | 南京文图景信息科技有限公司 | Multi-language place name root Chinese translation method based on Transformer deep learning model |
CN112966068A (en) * | 2020-11-09 | 2021-06-15 | 袭明科技(广东)有限公司 | Resume identification method and device based on webpage information |
CN112905595A (en) * | 2021-03-05 | 2021-06-04 | 腾讯科技(深圳)有限公司 | Data query method and device and computer readable storage medium |
Non-Patent Citations (2)
Title |
---|
颜 闻 等: "外语地名机器翻译中通专名区分技术研究", 《测绘地理信息》 * |
颜 闻 等: "机 器学习 的地名专名音译技术研究", 《测绘科学》 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116050420A (en) * | 2022-11-12 | 2023-05-02 | 武汉大学 | Chinese and French voice semantic recognition method and device based on preposition sentence |
CN116050420B (en) * | 2022-11-12 | 2023-09-22 | 武汉大学 | Chinese and French voice semantic recognition method and device based on preposition sentence |
CN117592462A (en) * | 2024-01-18 | 2024-02-23 | 航天宏图信息技术股份有限公司 | Correlation processing method and device for open source place name data based on place group |
CN117592462B (en) * | 2024-01-18 | 2024-04-16 | 航天宏图信息技术股份有限公司 | Correlation processing method and device for open source place name data based on place group |
Also Published As
Publication number | Publication date |
---|---|
CN113807105B (en) | 2023-07-21 |
AU2021104429A4 (en) | 2021-09-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10303761B2 (en) | Method, non-transitory computer-readable recording medium storing a program, apparatus, and system for creating similar sentence from original sentences to be translated | |
US9588960B2 (en) | Automatic extraction of named entities from texts | |
Evans | Applying machine learning toward an automatic classification of it | |
Simard et al. | Bilingual sentence alignment: Balancing robustness and accuracy | |
RU2636098C1 (en) | Use of depth semantic analysis of texts on natural language for creation of training samples in methods of machine training | |
CN113807105A (en) | French geographical name machine translation method | |
Gupta et al. | Text summarization of Hindi documents using rule based approach | |
CN113033183B (en) | Network new word discovery method and system based on statistics and similarity | |
CN110348003A (en) | The abstracting method and device of text effective information | |
US20100094615A1 (en) | Document translation apparatus and method | |
CN110196910B (en) | Corpus classification method and apparatus | |
CN114036929A (en) | Full-simple matching method based on multi-model feature fusion | |
JPWO2014002774A1 (en) | Synonym extraction system, method and recording medium | |
Kim et al. | Evaluating a pivot-based approach for bilingual lexicon extraction | |
JP2011008784A (en) | System and method for automatically recommending japanese word by using roman alphabet conversion | |
CN115455986A (en) | Spanish language place name translation method, device, equipment and medium | |
WO2021072848A1 (en) | Text information extraction method and apparatus, and computer device and storage medium | |
CN107590132B (en) | Method for automatically correcting part of characters-judging by English part of speech | |
Lu et al. | Learning Chinese word embeddings by discovering inherent semantic relevance in sub-characters | |
CN113705223A (en) | Personalized English text simplification method taking reader as center | |
CN111428475A (en) | Word segmentation word bank construction method, word segmentation method, device and storage medium | |
CN107679037B (en) | Word frequency-based digital publication vocabulary extraction method | |
Strankale et al. | Automatic Word Sense Mapping from Princeton WordNet to Latvian WordNet. | |
JP2010152420A (en) | Example matching translation device, program, and phrase translation device configured to include translation device | |
JP2009230561A (en) | Example-set-based translation device, method and program, and phrase translation device including the translation device |
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 |