Filters








2,008 Hits in 7.9 sec

Web Translation Mining Based on Suffix Arrays

Gaolin Fang, Hao Yu
2007 International Journal of Asian Language Processing  
Experiments on two test sets of 401 English-Chinese terms and 100 English-Japanese terms validate that our system has good performance.  ...  In this paper, after reviewing and analyzing all possible methods of acquiring translations, a statistics method based on suffix arrays is proposed to mine term translations from the Web.  ...  This system can automatically extract the translations of 405 complex terms in the tourism domain.  ... 
dblp:journals/jclc/FangY07 fatcat:mf5ejw55ubcn3klyett766z4uq

Web-Based Terminology Translation Mining [chapter]

Gaolin Fang, Hao Yu, Fumihito Nishino
2005 Lecture Notes in Computer Science  
Extensive experiments on two test sets of 401 and 3511 English terms validate that our system has better performance. 1) Acquiring translation from parallel corpora.  ...  In the proposed method, on the basis of an analysis of different forms of term translation distributions, character-based string frequency estimation is presented to construct term translation candidates  ...  This system can automatically extract the translations of 405 complex terms in the tourism domain.  ... 
doi:10.1007/11562214_87 fatcat:jhar4vf47ba3lgjefiwtgrbuei

Automatic acquisition of "noun+verb" idiomatic compounds in Korean

송상헌
2015 Linguistic Research  
In order to acquire the "noun+verb" idiomatic compounds in Korean in a fully automatic way, the current work exploits a syntax-annotated corpus (i.e. treebank) and three lexical hierarchies in Korean.  ...  The state-of-the-art skills of computational linguistics pay attention to lexical semantics, because it has a potential to be used to improve language processing systems in terms of coverage as well as  ...  The materials include the sets of lowest common subsumers, the list of the concept nodes most strongly associated with verbal items, the evaluation tables, and the whole entries of the "noun+verb" idiomatic  ... 
doi:10.17250/khisli.32.1.201504.009 fatcat:24sn42jgwzc5hmxpzgyoqn7e4y

Building a Korean-Vietnamese Neural Machine Translation System with Korean Morphological Analysis and Word Sense Disambiguation

Quang-Phuoc Nguyen, Anh-Dung Vo, Joon-Choul Shin, Phuoc Tran, Cheol-Young Ock
2019 IEEE Access  
INDEX TERMS Korean-Vietnamese machine translation, Korean-Vietnamese parallel corpus, lexical semantic network, morphological analysis, neural machine translation, word sense disambiguation.  ...  In this paper, we manually established a lexical semantic network for the special characteristics of Korean as a knowledge base that was used for developing our Korean morphological analysis and word-sense  ...  The translation results of the systems in terms of BLEU and TER scores are shown in Table 12 . 1) COMPARISON BETWEEN SMT AND NMT For both translation directions, NMT systems outperform SMT systems in  ... 
doi:10.1109/access.2019.2902270 fatcat:lezrz67ftzefjjnn3kvewleyqu

Semantically-Informed Syntactic Machine Translation: A Tree-Grafting Approach [article]

Kathryn Baker, Michael Bloodgood, Chris Callison-Burch, Bonnie J. Dorr, Nathaniel W. Filardo, Lori Levin, Scott Miller, Christine Piatko
2014 arXiv   pre-print
., in DARPA GALE) that both syntactic and semantic information are critical for improving translation quality---and further demonstrates that large gains can be achieved for low-resource languages with  ...  different word order than English.  ...  Acknowledgments We thank Aaron Phillips for help converting the output of the entity tagger for ingest by the tree-grafting program.  ... 
arXiv:1409.7085v1 fatcat:i63rydjyhbgilg6o5tvglfm2te

High-level methodologies for grammar engineering, introduction to the special issue

Denys Duchier, Yannick Parmentier
2015 Journal of Language Modelling  
Advances in the field have led to the development of environments for semi-automatic grammar engineering, borrowing ideas from compilation (grammar engineering is compared with software development) and  ...  textual entailment, dialogue systems, or machine translation.  ...  Still, data-driven approaches to grammar learning showed promising results for English, in particular in terms of coverage (Cahill et al. 2008) .  ... 
doi:10.15398/jlm.v3i1.117 fatcat:c2bo6drgmrg4pasyvgb5x7bmpq

CLiFF Notes: Research in the Language, Information and Computation Laboratory of the University of Pennsylvania [article]

Editors: Matthew Stone, Libby Levison
1995 arXiv   pre-print
Short abstracts by computational linguistics researchers at the University of Pennsylvania describing ongoing individual and joint projects.  ...  translate such structures between Korean and English; work on lexical selection in translating from Korean to English; and recovering dropped NPs in Korean in preparation for translating to English.  ...  Here, we are investigating how the basic idea of Synchronous TAG can be used for Korean to English and English to Korean translation.  ... 
arXiv:cmp-lg/9506008v1 fatcat:aidgv3pdzvfatc7yjygdvthcjq

A Survey on Awesome Korean NLP Datasets [article]

Byunghyun Ban
2021 arXiv   pre-print
produce a technology or product, suitable for Korean processing.  ...  Although benchmark tests with English datasets are sufficient to show off the performances of new models and methods, still a researcher need to train and validate the models on Korean based datasets to  ...  This Alignment Model for Extracting reflects the recent advance in popularity of Korean NLP English-Korean Translation of Term 24k dataset construction  ... 
arXiv:2112.01624v2 fatcat:xkq767m67nfypgz4nehle7pgci

Legal Concepts and Multilingual Contexts in Digital Information

Daniela Tiscornia, Maria Teresa Sagri
2012 Beijing Law Review  
semantic resources may have a strategic role in representing meaning evolution and in investigating social and cultural influences in linguistic uses and, as a further goal, solutions offered by ICT for  ...  borders, there is a strong demand of shared vocabularies embedding a shared understanding of legal concept.  ...  ); the transplant of the concept in the Korean Civil Code, translated in 친권, maintains the same meaning, as expressed by the English translation ("parents shall have parental authority of their minor  ... 
doi:10.4236/blr.2012.33010 fatcat:grbmq3nz7nhkdi2lv4yenpz5zu

Translation of Pronominal Anaphora between English and Spanish: Discrepancies and Evaluation

J. Peral, A. Ferrandez
2003 The Journal of Artificial Intelligence Research  
We have obtained a precision of 80.4% and 84.8% in the translation of Spanish and English pronouns, respectively.  ...  The translation of English and Spanish anaphoric third-person personal pronouns (including Spanish zero pronouns) into the target language has been evaluated on unrestricted corpora.  ...  We are also grateful for the helpful comments of the anonymous reviewers of several conference papers in which we presented our preliminary work.  ... 
doi:10.1613/jair.1115 fatcat:43yufeoyo5glvkyd6xhzrt2lwm

Getting Past the Language Gap: Innovations in Machine Translation [chapter]

Rodolfo Delmonte
2012 Mobile Speech and Advanced Natural Language Solutions  
in terms of improvements to the state of the art.  ...  in Machine Translation -.... there are three systems specifically for translating patents: the PaTrans and SpaTrans systems developed for LingTech A/S to translate English patents into Danish ...  ...  significant improvements of 2 BLEU points over baseline using technical translation data for French to English.  ... 
doi:10.1007/978-1-4614-6018-3_6 fatcat:2njkc6meabhaxosl4wircumfjm

Noun Sense Identification of Korean Nominal Compounds Based on Sentential Form Recove

Seong Il Yang
2010 ETRI Journal  
In this paper, we present a practical method for the sense tagging of Korean unit nouns in a nominal compound.  ...  This technique makes use of the characteristics of Korean predicative nouns.  ...  More than one million verb patterns were constructed manually for Korean-to-English translation in common and technical domains.  ... 
doi:10.4218/etrij.10.1510.0083 fatcat:hkbg6ifphjdqnc5rvyr3q2o42u

HPSG-Based Preprocessing for English-to-Japanese Translation

Hideki Isozaki, Katsuhito Sudoh, Hajime Tsukada, Kevin Duh
2012 ACM Transactions on Asian Language Information Processing  
For English-to-Japanese translation, we need a large distance limit to obtain acceptable translations, and the number of translation candidates is extremely large.  ...  the quality of English-to-Japanese translation.  ...  Yusuke Miyao for his useful advice on the usage of Enju. We thank the audience and the reviewers for their comments.  ... 
doi:10.1145/2334801.2334802 fatcat:dtju2hmsr5ghpjuisueertxfam

Transcending the Tower of Babel: Supporting Access to Multilingual Information with CrossLanguage Information Retrieval [chapter]

2010 Emergent Information Technologies and Enabling Policies for Counter-Terrorism  
English query term e p(f i |e) The probability that English term e translates to French term f i L d The number of French terms in document d L avg The average number of French terms in a document  ...  term f i occurs DF(e) Estimated number of translated documents that would have contained English term e N The number of documents in the collection T(e) The set of known French translations for  ... 
doi:10.1109/9780470874103.ch15 fatcat:x3h7odkjsnfublnv6uj75cgzbu

Transcending the Tower of Babel: Supporting Access to Multilingual Information with Cross-Language Information Retrieval [chapter]

Douglas W. Oard
2006 Emergent Information Technologies and Enabling Policies for Counter-Terrorism  
English query term e p(f i |e) The probability that English term e translates to French term f i L d The number of French terms in document d L avg The average number of French terms in a document  ...  term f i occurs DF(e) Estimated number of translated documents that would have contained English term e N The number of documents in the collection T(e) The set of known French translations for  ... 
doi:10.1002/047178656x.ch15 fatcat:64vv22a7gnhs5di372m6fmzrby
« Previous Showing results 1 — 15 out of 2,008 results