Filters








2,960 Hits in 7.2 sec

Correction of Errors in a Modality Corpus Used for Machine Translation by Using Machine-learning Method [article]

Masaki Murata, Masao Utiyama, Kiyotaka Uchimoto, Qing Ma, Hitoshi Isahara
2001 arXiv   pre-print
We performed corpus correction on a modality corpus for machine translation by using such machine-learning methods as the maximum-entropy method.  ...  We compared several kinds of methods for corpus correction in our experiments and developed a good method for corpus correction.  ...  Based on the above results, we think Conclusion In this paper, we have described corpus correction using a machine-learning method for a modality corpus for machine translation.  ... 
arXiv:cs/0105001v1 fatcat:dp324pkb3zaereu7hqdq7onyqe

Lexical Resources for Hindi Marathi MT [article]

Sreelekha S, Pushpak Bhattacharyya
2017 arXiv   pre-print
We have described case studies, evaluations and detailed error analysis for both Marathi to Hindi and Hindi to Marathi machine translation systems.  ...  In this paper we describe some ways to utilize various lexical resources to improve the quality of statistical machine translation system.  ...  Acknowledgements We thank Almighty and truth for this work. References  ... 
arXiv:1703.01485v1 fatcat:qzjylie5h5ablg777xmqb3b4km

ВИКОРИСТАННЯ ЦИФРОВИХ ТЕХНОЛОГІЙ ДЛЯ ВИПРАВЛЕННЯ ГРАМАТИЧНИХ ПОМИЛОК: СИНТАКСИЧНІ N-ГРАМИ ТА МЕТОДИ ГЛИБИННОГО НАВЧАННЯ

Олена Олександрівна ПОЖАРИЦЬКА, Кирило Володимирович ТРОЇЦЬКИЙ
2021 Мова  
Також у статті проаналізовано іншу модель, засновану на архітектурі трансформера — GECToR (Grammatical Error Correction: Tag, Not Rewrite).  ...  Speaking about grammatical error correction, machine translation methods can be used to translate the potentially wrong sentences into the correct ones.  ...  The statistic model is compared with one of the leading machine learning models for grammatical error correction according to BEA 2019 shared task -GECToR (Grammatical Error Correction: Tag, Not Rewrite  ... 
doi:10.18524/2307-4558.2021.35.237789 fatcat:hw3aunhhmvcwza533o6fgjglze

Automatic Inference of the Tense of Chinese Events Using Implicit Linguistic Information

Yuchen Zhang, Nianwen Xue
2014 Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)  
We propose three improvements over a relatively strong baseline method -a statistical learning method with extensive feature engineering.  ...  We use a new corpus annotated with Chinese semantic tense information and other implicit Chinese linguistic information using a "distant annotation" method.  ...  This work is supported by the National Science Foundation via Grant No. 0910532 entitled "Richer Representations for Machine Translation".  ... 
doi:10.3115/v1/d14-1204 dblp:conf/emnlp/ZhangX14 fatcat:vrhthsxbe5gmxajkupfnucv2em

Use of Modality and Negation in Semantically-Informed Syntactic MT [article]

Kathryn Baker, Michael Bloodgood, Bonnie J. Dorr, Chris Callison-Burch, Nathaniel W. Filardo, Christine Piatko, Lori Levin, Scott Miller
2015 arXiv   pre-print
Our annotation scheme isolates three components of modality and negation: a trigger (a word that conveys modality or negation), a target (an action associated with modality or negation) and a holder (an  ...  -2009) on Semantically-Informed Machine Translation (SIMT).  ...  Acknowledgments We thank Aaron Phillips for help with conversion of the output of the entity tagger for ingest by the tree-grafting program.  ... 
arXiv:1502.01682v1 fatcat:qliff2qekrhijflqscwle5mssi

Erroneous data generation for Grammatical Error Correction

Shuyao Xu, Jiehao Zhang, Jin Chen, Long Qin
2019 Proceedings of the Fourteenth Workshop on Innovative Use of NLP for Building Educational Applications  
It has been demonstrated that the utilization of a monolingual corpus in neural Grammatical Error Correction (GEC) systems can significantly improve the system performance.  ...  Our system achieved an F 0.5 of 66.61 in the BEA 2019 Shared Task: Grammatical Error Correction.  ...  Acknowledgments We thank Xiaoxue Fan, Miao Xue and Yueming Gao for their help in checking the three tables required for creating the Word Trees.  ... 
doi:10.18653/v1/w19-4415 dblp:conf/bea/XuZCQ19 fatcat:5fu2wxvstvgk7gzcukcpukbfoa

POSTECH Grammatical Error Correction System in the CoNLL-2014 Shared Task

Kyusong Lee, Gary Geunbae Lee
2014 Proceedings of the Eighteenth Conference on Computational Natural Language Learning: Shared Task  
Various methods are proposed to correct errors such as rule-based, probability n-gram vector approaches and router-based approach.  ...  Google N-gram count corpus is used mainly as the correction resource.  ...  A machine learning method will be used to train the router with various features.  ... 
doi:10.3115/v1/w14-1709 dblp:conf/conll/LeeL14 fatcat:4wqzs4f4c5gcrcnjnzsxl6ln2e

Editorial: Cognitive Linguistics in Chinese Teaching and Learning

2021 International Journal of Chinese Language Teaching  
Embracing a wide range of research methods, the CL approach is interdisciplinary in nature and constantly enriching itself based on new empirical results.  ...  Applying Cognitive Linguistics Insights to LTeaching and Learning Concepts in CL have been successfully adapted to support L2 teaching and learning in the areas of the semantics of English prepositions  ...  Chinese modal verbs 能 néng, 可以 kěyǐ, and 可能 kěnéng often are all translated as the English modal verb can.  ... 
doi:10.46451/ijclt.2021.10.01 fatcat:wt66zza3xvaollnh5gp2opnbmm

Choosing the Right Word: Using Bidirectional LSTM Tagger for Writing Support Systems [article]

Victor Makarenkov, Lior Rokach, Bracha Shapira
2019 arXiv   pre-print
While state-of-the-art grammatical error correction uses error-specific classifiers and machine translation methods, we demonstrate an unsupervised method that is based solely on a high quality text corpus  ...  In this paper we present a novel machine learning based application for proper word choice task.  ...  ACKNOWLEDGEMENTS We would like to express our gratitude to Stas Shteibook and Evgenyi Vainer for their invaluable technical support in setting up the GPU machine and compiling the DyNet toolkit in the  ... 
arXiv:1901.02490v1 fatcat:27n56zzewjhplf4puhisard7q4

Modality and Negation in SIMT Use of Modality and Negation in Semantically-Informed Syntactic MT

Kathryn Baker, Michael Bloodgood, Bonnie J. Dorr, Chris Callison-Burch, Nathaniel W. Filardo, Christine Piatko, Lori Levin, Scott Miller
2012 Computational Linguistics  
Our annotation scheme isolates three components of modality and negation: a trigger (a word that conveys modality or negation), a target (an action associated with modality or negation) and a holder (an  ...  -2009) on Semantically-Informed Machine Translation (SIMT).  ...  Acknowledgments We thank Aaron Phillips for help with conversion of the output of the entity tagger for ingest by the tree-grafting program.  ... 
doi:10.1162/coli_a_00099 fatcat:22t5zht6bzhqbluutawiztjjvm

Using TectoMT as a Preprocessing Tool for Phrase-Based Statistical Machine Translation [chapter]

Daniel Zeman
2010 Lecture Notes in Computer Science  
We describe how TectoMT, a successful framework for analysis and generation of language, can be used as preprocessor for a phrasebased MT system.  ...  We present a systematic comparison of preprocessing techniques for two language pairs: English-Czech and English-Hindi.  ...  The work on this project has been supported by the grant MSM0021620838 by the Czech Ministry of Education.  ... 
doi:10.1007/978-3-642-15760-8_28 fatcat:ee27wbvfrvh25eaqlbiwiusngy

Correction of Verbs in English Corpus by using the Concept of AI

M MSRauthan, Sumit Khulbe, H S Dhami
2012 International Journal of Computer Applications  
The present paper aims at automated correction of verb from huge English corpus and addition of verbs at run time through single sentence.  ...  In support of this discussion, and approaches we evaluate Natural Language Processing (NLP) systems and these are addressed with the help of hierarchical inheritance.  ...  We have use recursive functions to correct the database errors and have formulated them with respect to the following three rules and apply them to understand in machine translation: a V (b V c) = (a  ... 
doi:10.5120/9705-4155 fatcat:p2sactnt3ffdvbukj7gowzytoy

English Grammar Error Detection Using Recurrent Neural Networks

Zhenhui He, Mian Ahmad Jan
2021 Scientific Programming  
The existing literature shows that the error of verb consistency and the error of verb tense are the two types of grammatical errors with the highest error rate in English composition.  ...  The verification results show the superiority of the proposed algorithm in verb error detection.  ...  Grammatical error correction is similar to the process of machine translation, in which there are many lessons to be learned, and its development is also similar.  ... 
doi:10.1155/2021/7058723 fatcat:xg34lacj6rh55nuo3f2gf5dcta

ADAPTING HYBRID MACHINE TRANSLATION TECHNIQUES FOR CROSS-LANGUAGE TEXT RETRIEVAL SYSTEM

P. ISWARYA, V. RADHA
2017 Journal of Engineering Science and Technology  
The hybrid machine translation system is a combination of rule based and statistical based approaches.  ...  To handle these issues, proposed architecture is designed in such a way that, it contains Improved Part-of-Speech tagger, machine learning based morphological analyser, collocation based word sense disambiguation  ...  Adapting Hybrid Machine Translation Techniques Cross-Language Text . . . . 659 Journal of Engineering Science and Technology March 2017, Vol. 12(3) Transliteration with error correction Transliteration  ... 
doaj:09b50c704a91433ea8d9fdc53d47d931 fatcat:rk2uw45sr5emjazuqmj7uab2km

System Combination for Grammatical Error Correction

Raymond Hendy Susanto, Peter Phandi, Hwee Tou Ng
2014 Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)  
Most of these approaches are based on classification or statistical machine translation (SMT).  ...  In this paper, we propose to combine the output from a classification-based system and an SMT-based system to improve the correction quality.  ...  We would like to thank Christopher Bryant for his comments on this paper.  ... 
doi:10.3115/v1/d14-1102 dblp:conf/emnlp/SusantoPN14 fatcat:alkuyb7jx5bwpkzadnh6geqrzi
« Previous Showing results 1 — 15 out of 2,960 results