AU2021104429A4 - Machine Translation Method for French Geographical Names - Google Patents
Machine Translation Method for French Geographical Names Download PDFInfo
- Publication number
- AU2021104429A4 AU2021104429A4 AU2021104429A AU2021104429A AU2021104429A4 AU 2021104429 A4 AU2021104429 A4 AU 2021104429A4 AU 2021104429 A AU2021104429 A AU 2021104429A AU 2021104429 A AU2021104429 A AU 2021104429A AU 2021104429 A4 AU2021104429 A4 AU 2021104429A4
- Authority
- AU
- Australia
- Prior art keywords
- french
- geographical
- generic term
- geographical name
- term
- 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.)
- Ceased
Links
- 238000013519 translation Methods 0.000 title claims abstract description 40
- 238000000034 method Methods 0.000 title claims abstract description 21
- 238000013518 transcription Methods 0.000 claims abstract description 51
- 230000035897 transcription Effects 0.000 claims abstract description 51
- 238000000354 decomposition reaction Methods 0.000 claims description 18
- 238000007781 pre-processing Methods 0.000 claims description 4
- 230000011218 segmentation Effects 0.000 claims description 3
- 230000014616 translation Effects 0.000 description 28
- 230000006870 function Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
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 TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Probability & Statistics with Applications (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Machine Translation (AREA)
Abstract
The present disclosure provides a machine translation method for French geographical names,
including: distinguishing a generic term and a specific term in a preprocessed French geographical
name phrase; translating the specific term based on letter combinations in a French-Chinese
transcription key to obtain a transcription result of the specific term; translating the generic term
based on a geographical entity category indicated by the generic term to obtain a transcription result
of the generic term; and combining the transcription result of the specific term and the transcription
result of the generic term to obtain a geographical name translation result. The technical solutions
provided in the present disclosure implement machine translation, reduce manpower consumption
when geographical names are generated, and improve translation efficiency of French geographical
names.
ABSTRACT DRAWING
Si
Obtain a French geographical name phrase to be translated
S2
Preprocess the French geographical name phrase
S3
Distinguish a generic term and a specific term in a preprocessed French
geographical name phrase
S4
Translate the specific term based on letter combinations in a French-Chinese
transcription key to obtain a transcription result of the specific term
Translate the generic term based on a geographical entity category S5
indicated by the generic term to obtain a transcription result of the generic
term
S6
Combine the transcription result of the specific term and the transcription
result of the generic term to obtain a geographical name translation result
FIG. 1
Description
[01] The present disclosure relates to the technical field of geographical name translation, and in particular, to a machine translation method for French geographical names.
[02] Translation of a geographical name is to convert an expression of a geographical entity from one language to another language. Generally, a geographical name is divided into two parts: a generic term and a specific term. The generic term summarizes commonness of surface features, which plays a role in category definition. The specific term refers to a specific geographical entity and is used to distinguish a same category of surface features, which plays a role in positioning. Automatic translation or machine translation of geographical names is part of named entity translation in the machine translation. However, this part is the most difficult one among all the machine translation of named entities. Firstly, composition of geographical names is complex, and composition of geographical names at different scales is significantly different. In addition, translation of geographical names includes free translation of generic terms and transcription of specific terms. Many general machine translations cannot address the problem in geographical name translation on their own. Currently, French geographical names are mainly translated manually, and thus efficiency is low.
[03] The present disclosure provides a machine translation method for French geographical names to improve translation efficiency of French geographical names.
[04] To achieve the above objective, the present disclosure provides a machine translation method for French geographical names, including:
[05] obtaining a French geographical name phrase to be translated;
[06] preprocessing the French geographical name phrase;
[07] distinguishing a generic term and a specific term in a preprocessed French geographical name phrase;
[08] translating the specific term based on letter combinations in a French-Chinese transcription key to obtain a transcription result of the specific term;
[09] translating the generic term based on a geographical entity category indicated by the generic term to obtain a transcription result of the generic term; and
[10] combining the transcription result of the specific term and the transcription result of the generic term to obtain a geographical name translation result.
[11] Optionally, the distinguishing a generic term and a specific term in the preprocessed French geographical name phrase may specifically include:
[12] determining generic term templates based on the preprocessed French geographical name phrases stored in a geographical name corpus;
[13] determining all generic term structure decomposition schemes based on the generic term templates;
[14] calculating logarithmic frequencies of the generic term templates;
[15] summing logarithmic frequencies in the same generic term structure decomposition scheme to obtain logarithmic frequency sums corresponding to the generic term structure decompositionschemes;
[16] using the generic term structure decomposition scheme with a largest logarithmic frequency sum as a geographical name structure tree; and
[17] using a leaf node of the geographical name structure tree as the specific term and a non leaf node of the geographical name structure tree as the generic term.
[18] Optionally, the determining generic term templates based on preprocessed French geographical name phrases stored in a geographical name corpus may specifically include:
[19] calculating mutual information of any ordered word pair in the geographical name corpus MIab Pab by using PaP , where Pa represents an occurrence frequency of a preprocessed French geographical name phrase a in the geographical name corpus, Pb represents an occurrence frequency of a preprocessed French geographical name phrase b in the geographical name corpus, ab represents a co-occurrence frequency of the preprocessed French geographical name phrases
a and b, and MIab represents mutual information of an ordered word pair (a, b); and the preprocessed French geographical name phrases a and b form the ordered word pair (a, b);
[20] storing ordered word pairs with a co-occurrence frequency greater than a first specified value and mutual information greater than a second specified value in the geographical name corpus into an ordered word pair library;
[21] traversing all sentences and using preprocessed French geographical name phrases in each sentence as vertices on a directed acyclic graph; and when two preprocessed French geographical name phrases in the sentence belong to an ordered word pair in the ordered word pair library, connecting the two vertices to draw a directed edge on the directed acyclic graph;
[22] finding all paths on the directed acyclic graph and generating a candidate geographical name template for each path based on a preprocessed French geographical name phrase corresponding to an accessed node, where the path consists of multiple directed edges; and
[23] counting a frequency of each candidate geographical name template and using candidate geographical name templates with a frequency greater than a specified frequency threshold as the generic term templates.
[24] Optionally, the translating the specific term based on letter combinations in a French Chinese transcription key to obtain a transcription result of the specific term may specifically include:
[25] performing unsupervised learning on word letters based on a principle of minimum entropy to obtain letter combination distribution;
[26] using a shortest path word segmentation method to segment letters in the specific term to obtain multiple sets of letter combinations;
[27] calculating average entropy of each set of letter combinations based on the letter combination distribution;
[28] selecting letter combinations with smallest entropy as optimal letter combinations; and
[29] transcribing the optimal letter combinations to Chinese characters based on the French Chinese transcription key to obtain the transcription result of the specific term.
[30] Optionally, the translating the generic term based on a geographical entity category indicated by the generic term to obtain a transcription result of the generic term may specifically include:
[31] using a French-Chinese dictionary and the generic term templates to translate and parse the generic term to obtain a geographical name hierarchical grammatical structure; and
[32] converting French geographical name elements in the geographical name hierarchical grammatical structure into Chinese geographical name elements layer by layer based on a bottom up principle to obtain the transcription result of the generic term.
[33] The present disclosure provides a machine translation method for French geographical names, including: distinguishing a generic term and a specific term in a preprocessed French geographical name phrase; translating the specific term based on letter combinations in a French Chinese transcription key to obtain a transcription result of the specific term; translating the generic term based on a geographical entity category indicated by the generic term to obtain a transcription result of the generic term; and combining the transcription result of the specific term and the transcription result of the generic term to obtain a geographical name translation result. The technical solutions provided in the present disclosure implement machine translation, reduce manpower consumption when geographical names are generated, and improve translation efficiency of French geographical names.
[34] In order to explain the technical solutions in embodiments of the present disclosure or in the prior art more clearly, the accompanying drawings required in the embodiments will be described below briefly. Apparently, the accompanying drawings in the following description show merely some embodiments of the present disclosure, and other drawings can be derived from these accompanying drawings by those of ordinary skill in the art without creative efforts.
[35] FIG. 1 is a flowchart of a machine translation method for French geographical names according to the present disclosure;
[36] FIG. 2 is a flowchart of distinguishing a generic term and a specific term in a geographical name according to the present disclosure;
[37] FIG. 3 is a flowchart of determining generic term templates based on preprocessed French geographical name phrases stored in a geographical name corpus;
[38] FIG. 4 is a flowchart of transcribing a specific term according to the present disclosure; and
[39] FIG. 5 is a flowchart of transcribing a generic term according to the present disclosure.
[40] The technical solutions of the embodiments of the present disclosure are clearly and completely described below with reference to the accompanying drawings. Apparently, the described embodiments are merely a part rather than all of the embodiments of the present disclosure. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments of the present disclosure without creative efforts shall fall within the protection scope of the present disclosure.
[41] The present disclosure provides a machine translation method for French geographical names to improve translation efficiency of French geographical names.
[42] To make the foregoing objective, features, and advantages of the present disclosure clearer and more comprehensible, the present disclosure will be further described in detail below with reference to the accompanying drawings and specific embodiments.
[43] As shown in FIG. 1, a machine translation method for French geographical names provided in the present disclosure includes the following steps:
[44] Step Sl: Obtaining a French geographical name phrase to be translated, where the French geographical name phrase is a phrase that contains a French geographical name.
[45] Step S2: Preprocessing the French geographical name phrase.
[46] Step S3: Distinguishing a generic term and a specific term in the preprocessed French geographical name phrase.
[47] Step S4: Translating the specific term based on letter combinations in a French-Chinese transcription key to obtain a transcription result of the specific term.
[48] Step S5: Translating the generic term based on a geographical entity category indicated by the generic term to obtain a transcription result of the generic term.
[49] Step S6: Combining the transcription result of the specific term and the transcription result of the generic term to obtain a geographical name translation result.
[50] Each step is described in detail below.
[51] Step S2: Preprocessing the French geographical name phrase. The French geographical name phrase may contain articles, symbols, illegal characters, and the like that are not conducive to geographical name machine translation. Therefore, in the present disclosure, special symbols such as articles, illegal letters, and punctuation marks that are not conducive to geographical name machine translation are removed before the generic term and specific term are distinguished. This improves accuracy of subsequent distinguishing the generic term and specific term.
[52] As shown in FIG. 2 and FIG. 3, step S3 of distinguishing the generic term and the specific term in the preprocessed French geographical name phrase may specifically include the following steps:
[53] Step S31: Determining generic term templates based on preprocessed French geographical name phrases stored in a geographical name corpus, which may specifically include the following steps:
[54] Step S311: Calculating mutual information of any ordered word pair in the geographical Pab MIab __ name corpus by using the following formula: Papb , where Pa represents an occurrence frequency of a preprocessed French geographical name phrase a in the geographical name corpus, b represents an occurrence frequency of a preprocessed French geographical name phrase b in the geographical name corpus, Pab represents a co-occurrence frequency of the preprocessed French geographical name phrases a and b, and MIab represents mutual informationof an ordered word pair (a, b). The preprocessed French geographical name phrases a and b form the ordered word pair (a, b).
[55] Step S312: Storing ordered word pairs with a co-occurrence frequency Pab greater than a first specified value T1 and mutual information MIab greater than a second specified value 2 in the geographical name corpus into an ordered word pair library G.
[56] Step S313: Traversing all sentences and using preprocessed French geographical name phrases in each sentence as vertices on a directed acyclic graph; and when two preprocessed French geographical name phrases in the sentence belong to an ordered word pair in the ordered word pair library, connecting the two vertices to draw a directed edge a -- b on the directed acyclic graph.
[57] Step S314: Finding all paths on the directed acyclic graph and generating a candidate geographical name template for each path based on a preprocessed French geographical name phrase corresponding to an accessed node, where the path consists of multiple directed edges. In this embodiment, if an adjacent node is crossed, a placeholder is inserted.
[58] Step S315: Counting a frequency of each candidate geographical name template and using candidate geographical name templates with a frequency greater than a specified frequency threshold as the generic term templates.
[59] Step S32: Determining all generic term structure decomposition schemes based on the generic term templates.
[60] Step S33: Calculating logarithmic frequencies of the generic term templates.
[61] Step S34: Summing logarithmic frequencies in the same generic term structure decomposition scheme to obtain logarithmic frequency sums corresponding to the generic term structure decomposition schemes.
[62] Step S35: Using the generic term structure decomposition scheme with a largest logarithmic frequency sum as a geographical name structure tree.
[63] Step S36: Using a leaf node of the geographical name structure tree as the specific term and a non-leaf node of the geographical name structure tree as the generic term.
[64] Specifically, generic term templates obtained for a given preprocessed French geographical name phrase by performing step S31 are used to decompose a structure of the preprocessed French geographical name phrase to generate a geographical name structure tree. To decompose the structure of the preprocessed French geographical name phrase, the present disclosure proposes the following structure decomposition hypotheses based on the projective hypothesis of syntactic analysis:
[65] 1. The preprocessed French geographical name phrase is composed of multiple generic term templates, which do not intersect each other.
[66] 2. A placeholder in a geographical name template is a generic term template.
[67] 3. Each preprocessed French geographical name phrase alone can be regarded as a special generic term template.
[68] Based on the above hypotheses, the present disclosure proposes a method for decomposing a structure of a geographical name phrase as follows: finding a series of generic term templates to cover each word in the geographical name phrase without repetition, omission, and intersection, to maximize a sum of logarithmic frequencies of the generic term templates. The method may specifically include the following two steps:
[69] 1. Performing scanning to obtain all possible geographical name templates in geographical name entries.
[70] 2. Traversing all legal structure decomposition schemes based on all the possible generic term templates; calculating a logarithmic frequency of each structure decomposition scheme (i.e., taking logarithm on frequency), which may specifically include: calculating a sum of logarithmic frequencies of all generic term templates in the structure decomposition scheme to obtain logarithmic frequencies of the generic term structure decomposition schemes; and selecting a structure decomposition scheme with the largest logarithmic frequency as a geographical name structure tree.
[71] In the geographical name structure tree, a non-leaf node is regarded as a generic term, and a leaf node is regarded as a candidate specific term based on the structure decomposition hypotheses, to identify the generic and specific terms through classification.
[72] As shown in FIG. 4, step S4 of translating the specific term based on the letter combinations in the French-Chinese transcription key to obtain the transcription result of the specific term may specifically include:
[73] Step S41: Performing unsupervised learning on word letters based on a principle of minimum entropy to obtain letter combination distribution.
[74] Step S42: Using a shortest path word segmentation method to segment letters in the specific term to obtain multiple sets of letter combinations. In the present disclosure, the letter combinations need to be as few as possible to make the transcription result as brief as possible.
[75] Step S43: Calculating average entropy of each set of letter combinations based on the letter combination distribution.
[76] Entropy is a measure of an amount of information contained in a variable. For a random variable x, its probability density function (distribution) is P, and its entropy is expressed as E = -f P(x)logP(x). In discrete cases, its entropy can also be expressed as E = -ZP(x)logP(x). The principle of minimum entropy is to minimize the entropy E by modifying the probability density function (distribution) and to achieve minimum redundant information contained in the variable.
[77] In the present disclosure, average entropy of letters E =- rP(X)1ogP(X) isdefined, where P(x) represents a distribution of probability at which a letter combination x appears in a corpus, and I'represents a set of letter combinations. Therefore, the average entropy of each set of letter combinations can be expressed as follows:
E ZX 0 P(x)ogP(x) 1781 X0 P(x) log*lIx
[79] where P(x) represents a distribution of probability at which the letter combination x appears in the corpus, Ix represents a length of the letter combination, namely, a number of letters in the letter combination, ) represents a set of letter combinations, and E represents the average entropy of each set of letter combinations.
[80] Step S44: Selecting letter combinations with the smallest entropy as the optimal letter combinations.
[81] Step S45: Transcribing the optimal letter combinations to Chinese characters based on the French-Chinese transcription key to obtain the transcription result of the specific term. Currently, this rule mainly uses the French-Chinese transcription key instituted by China in Transformation Guidelines of Geographical Names from Foreign Languages into Chinese of standard No. GB/T 17693.3-1999.
[82] As shown in FIG. 5, step S5 of translating the generic term based on the geographical entity category indicated by the generic term to obtain the transcription result of the generic term may specifically include the following steps:
[83] Step S51: Using a French-Chinese dictionary and the generic term templates to translate and parse the generic term to obtain a geographical name hierarchical grammatical structure.
[84] Step S52: Converting French geographical name elements in the geographical name hierarchical grammatical structure into Chinese geographical name elements layer by layer based on a bottom-up principle to obtain the transcription result of the generic term.
[85] In this specification, several specific embodiments are used for illustration of the principles and implementations of the present disclosure. The description of the foregoing embodiments is used to help illustrate the method of the present disclosure and the core ideas thereof. In addition, persons of ordinary skill in the art can make various modifications in terms of specific implementations and the scope of application in accordance with the ideas of the present disclosure. In conclusion, the content of this specification shall not be construed as a limitation to the present disclosure.
Claims (5)
1. A machine translation method for French geographical names, comprising: obtaining a French geographical name phrase to be translated; preprocessing the French geographical name phrase; distinguishing a generic term and a specific term in a preprocessed French geographical name phrase; translating the specific term based on letter combinations in a French-Chinese transcription key to obtain a transcription result of the specific term; translating the generic term based on a geographical entity category indicated by the generic term to obtain a transcription result of the generic term; and combining the transcription result of the specific term and the transcription result of the generic term to obtain a geographical name translation result.
2. The machine translation method for French geographical names according to claim 1, wherein the distinguishing a generic term and a specific term in the preprocessed French geographical name phrase specifically comprises: determining generic term templates based on the preprocessed French geographical name phrases stored in a geographical name corpus; determining all generic term structure decomposition schemes based on the generic term templates; calculating logarithmic frequencies of the generic term templates; summing logarithmic frequencies in the same generic term structure decomposition scheme to obtain logarithmic frequency sums corresponding to the generic term structure decomposition schemes; using the generic term structure decomposition scheme with a largest logarithmic frequency sum as a geographical name structure tree; and using a leaf node of the geographical name structure tree as the specific term and a non-leaf node of the geographical name structure tree as the generic term.
3. The machine translation method for French geographical names according to claim 2, wherein the determining generic term templates based on preprocessed French geographical name phrases stored in a geographical name corpus specifically comprises: calculating mutual information of any ordered word pair in the geographical name corpus by
MIab __ Pab using PaPb , wherein Pa represents an occurrence frequency of a preprocessed French
geographical name phrase a in the geographical name corpus, Pb represents an occurrence frequency of a preprocessed French geographical name phrase b in the geographical name corpus, ab represents a co-occurrence frequency of the preprocessed French geographical name phrases
a and b, and MIab represents mutual information of an ordered word pair (a, b); and the preprocessed French geographical name phrases a and b form the ordered word pair (a, b); storing ordered word pairs with a co-occurrence frequency greater than a first specified value and mutual information greater than a second specified value in the geographical name corpus into an ordered word pair library; traversing all sentences and using preprocessed French geographical name phrases in each sentence as vertices on a directed acyclic graph; and when two preprocessed French geographical name phrases in the sentence belong to an ordered word pair in the ordered word pair library, connecting the two vertices to draw a directed edge on the directed acyclic graph; finding all paths on the directed acyclic graph and generating a candidate geographical name template for each path based on a preprocessed French geographical name phrase corresponding to an accessed node, wherein the path consists of multiple directed edges; and counting a frequency of each candidate geographical name template and using candidate geographical name templates with a frequency greater than a specified frequency threshold as the generic term templates.
4. The machine translation method for French geographical names according to claim 1, wherein the translating the specific term based on letter combinations in a French-Chinese transcription key to obtain a transcription result of the specific term specifically comprises: performing unsupervised learning on word letters based on a principle of minimum entropy to obtain letter combination distribution; using a shortest path word segmentation method to segment letters in the specific term to obtain multiple sets of letter combinations; calculating average entropy of each set of letter combinations based on the letter combination distribution; selecting letter combinations with smallest entropy as optimal letter combinations; and transcribing the optimal letter combinations to Chinese characters based on the French-Chinese transcription key to obtain the transcription result of the specific term.
5. The machine translation method for French geographical names according to claim 2, wherein the translating the generic term based on a geographical entity category indicated by the generic term to obtain a transcription result of the generic term specifically comprises: using a French-Chinese dictionary and the generic term templates to translate and parse the generic term to obtain a geographical name hierarchical grammatical structure; and converting French geographical name elements in the geographical name hierarchical grammatical structure into Chinese geographical name elements layer by layer based on a bottom up principle to obtain the transcription result of the generic term.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| AU2021104429A AU2021104429A4 (en) | 2021-07-22 | 2021-07-22 | Machine Translation Method for French Geographical Names |
| CN202111122788.XA CN113807105B (en) | 2021-07-22 | 2021-09-24 | French place name machine translation method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| AU2021104429A AU2021104429A4 (en) | 2021-07-22 | 2021-07-22 | Machine Translation Method for French Geographical Names |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| AU2021104429A4 true AU2021104429A4 (en) | 2021-09-16 |
Family
ID=77666647
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| AU2021104429A Ceased AU2021104429A4 (en) | 2021-07-22 | 2021-07-22 | Machine Translation Method for French Geographical Names |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN113807105B (en) |
| AU (1) | AU2021104429A4 (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| 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 |
Family Cites Families (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 |
| CN102253930B (en) * | 2010-05-18 | 2016-03-23 | 腾讯科技（深圳）有限公司 | A kind of method of text translation and device |
| CN109829173B (en) * | 2019-01-21 | 2023-09-29 | 中国测绘科学研究院 | English place name translation method and device |
| CN111709238B (en) * | 2020-06-04 | 2023-04-07 | 中国地质大学（北京） | Web page geoscience correlation calculation method based on geoscience expert knowledge |
| CN112084796B (en) * | 2020-09-15 | 2021-04-09 | 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 |
-
2021
- 2021-07-22 AU AU2021104429A patent/AU2021104429A4/en not_active Ceased
- 2021-09-24 CN CN202111122788.XA patent/CN113807105B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN113807105A (en) | 2021-12-17 |
| CN113807105B (en) | 2023-07-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Evans | Applying machine learning toward an automatic classification of it | |
| US6760695B1 (en) | Automated natural language processing | |
| Lee et al. | English to Korean statistical transliteration for information retrieval | |
| AU2021104429A4 (en) | Machine Translation Method for French Geographical Names | |
| CN113033183B (en) | Network new word discovery method and system based on statistics and similarity | |
| Kumar et al. | A study of spell checking techniques for indian languages | |
| Chang | A new approach for automatic Chinese spelling correction | |
| Ratnaparkhi et al. | A maximum entropy model for parsing. | |
| US20100094615A1 (en) | Document translation apparatus and method | |
| Sreeram et al. | Exploration of end-to-end framework for code-switching speech recognition task: Challenges and enhancements | |
| Pham | Parts of speech tagging: Rule-based | |
| JPWO2014002774A1 (en) | Synonym extraction system, method and recording medium | |
| Zhang et al. | Design and implementation of Chinese Common Braille translation system integrating Braille word segmentation and concatenation rules | |
| Chaudhuri | Reversed word dictionary and phonetically similar word grouping based spell-checker to Bangla text | |
| Imamura et al. | Predicate-argument structure analysis with zero-anaphora resolution for dialogue systems | |
| WO1997040453A1 (en) | Automated natural language processing | |
| Kuo et al. | A phonetic similarity model for automatic extraction of transliteration pairs | |
| Rosset et al. | The LIMSI participation in the QAst track | |
| CN115455986A (en) | Spanish language place name translation method, device, equipment and medium | |
| Alshawi et al. | Head-transducer models for speech translation and their automatic acquisition from bilingual data | |
| Yin et al. | Research of POS tagging rules mining algorithm | |
| CN113536776A (en) | Confusion statement generation method, terminal device and computer-readable storage medium | |
| Bilac et al. | Direct combination of spelling and pronunciation information for robust back-transliteration | |
| Lee et al. | Automatic construction of real‐world‐based typing‐error test dataset | |
| Hajič | Linguistics meets exact sciences |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| FGI | Letters patent sealed or granted (innovation patent) | ||
| MK22 | Patent ceased section 143a(d), or expired - non payment of renewal fee or expiry |