ABSTRACT
Grammatical Error Correction (GEC) task is always considered as low resource machine translation task which translates a sentence in an ungrammatical language to a grammatical language. As the state-of-the-art approach to GEC task, transformer-based neural machine translation model takes input sentence as a token sequence without sentence's structure information, and may be misled by some strange ungrammatical contexts. In response, to lay more attention on a given token's correct collocation rather than the misleading tokens, we propose dependent self-attention to relatively increase the attention score between correct collocations according to the dependency distance between tokens. However, as the source sentence is ungrammatical in GEC task, the correct collocations can hardly be extracted by normal dependency parser. Therefore, we propose dependency parser for ungrammatical sentence to get the dependency distance between tokens in the ungrammatical sentence. Our method achieves competitive results on both BEA-2019 shared task, CoNLL-2014 shared task and JFLEG test sets.
Supplemental Material
- Abhijeet Awasthi, Sunita Sarawagi, Rasna Goyal, Sabyasachi Ghosh, and Vihari Piratla. 2019. Parallel iterative edit models for local sequence transduction. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). Hong Kong, China, 4260--4270.Google ScholarCross Ref
- Christopher Bryant, Mariano Felice, Øistein E. Andersen, and Ted Briscoe. 2019. The BEA-2019 shared task on grammatical error correction. In Proceedings of the Fourteenth Workshop on Innovative Use of NLP for Building Educational Applications. Florence, Italy, 52--75.Google ScholarCross Ref
- Christopher Bryant, Mariano Felice, and Ted Briscoe. 2017. Automatic annotation and evaluation of error types for grammatical error correction. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Vancouver, Canada, 793--805.Google ScholarCross Ref
- Yo Joong Choe, Jiyeon Ham, Kyubyong Park, and Yeoil Yoon. 2019. A neural grammatical error correction system built on better pre-training and sequential transfer learning. In Proceedings of the Fourteenth Workshop on Innovative Use of NLP for Building Educational Applications. Florence, Italy, 213--227.Google ScholarCross Ref
- Shamil Chollampatt and Hwee Tou Ng. 2018. A multilayer convolutional encoder-decoder neural network for grammatical error correction. In Proceedings of the Thirty-Second AAAI Conf. on Artificial Intelligence. New Orleans, USA, 5755--5762. Google ScholarDigital Library
- Michael Collins. 2002. Discriminative training methods for hidden markov models: theory and experiments with perceptron algorithms. In Proceedings of the 2002 Conference on Empirical Methods in Natural Language Processing (EMNLP 2002). 1--8. Google ScholarDigital Library
- Fabien Cromieres, Chenhui Chu, Toshiaki Nakazawa, and Sadao Kurohashi. 2016. Kyoto University participation to WAT 2016. In Proceedings of the 3rd Workshop on Asian Translation (WAT2016). Osaka, Japan, 166--174.Google Scholar
- Daniel Dahlmeier and Hwee Tou Ng. 2012. Better evaluation for grammatical error correction. In Proceedings of the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Montréal, Canada, 568--572. Google ScholarDigital Library
- Daniel Dahlmeier, Hwee Tou Ng, and Siew Mei Wu. 2013. Building a large annotated corpus of learner English: The NUS Corpus of Learner English. In Proceedings of the Eighth Workshop on Innovative Use of NLP for Building Educational Applications. Atlanta, Georgia, 22--31.Google Scholar
- Daniel Fernández-González and Carlos Gómez-Rodr'iguez. 2019. Left-to-Right dependency parsing with pointer networks. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Vol. 1 (Long and Short Papers). Minneapolis, Minnesota, 710--716.Google ScholarCross Ref
- Jennifer Foster and Oistein Andersen. 2009. GenERRate: generating errors for use in grammatical error Detection. In Proceedings of the Fourth Workshop on Innovative Use of NLP for Building Educational Applications. Boulder, Colorado, 82--90. Google ScholarDigital Library
- Matt Gardner, Joel Grus, Mark Neumann, Oyvind Tafjord, Pradeep Dasigi, Nelson F. Liu, Matthew Peters, Michael Schmitz, and Luke Zettlemoyer. 2018. AllenNLP: a deep semantic natural language processing platform. In Proceedings of Workshop for NLP Open Source Software (NLP-OSS). Melbourne, Australia, 1--6.Google ScholarCross Ref
- Tao Ge, Furu Wei, and Ming Zhou. 2018. Fluency boost learning and inference for neural grammatical error correction. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Melbourne, Australia, 1055--1065.Google ScholarCross Ref
- Yoav Goldberg and Michael Elhadad. 2010. An efficient algorithm for easy-first non-directional dependency parsing. In Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics. Los Angeles, CA, 742--750. Google ScholarDigital Library
- Roman Grundkiewicz, Marcin Junczys-Dowmunt, and Kenneth Heafield. 2019. Neural grammatical error correction systems with unsupervised pre-training on synthetic data. In Proceedings of the Fourteenth Workshop on Innovative Use of NLP for Building Educational Applications. Florence, Italy, 252--263.Google ScholarCross Ref
- Homa B. Hashemi and Rebecca Hwa. 2016. An evaluation of parser robustness for ungrammatical sentences. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing. Austin, Texas, 1765--1774.Google Scholar
- Homa B. Hashemi and Rebecca Hwa. 2018. Jointly parse and fragment ungrammatical sentences. In Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence. New Orleans, USA, 5165--5172.Google Scholar
- Marcin Junczys-Dowmunt, Roman Grundkiewicz, Shubha Guha, and Kenneth Heafield. 2018. Approaching neural grammatical error correction as a low-resource machine translation task. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers). New Orleans, Louisiana, 595--606.Google ScholarCross Ref
- Masahiro Kaneko, Masato Mita, Shun Kiyono, Jun Suzuki, and Kentaro Inui. 2020. Encoder-Decoder models can benefit from pre-trained masked language models in grammatical error correction. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Online, 4248--4254.Google ScholarCross Ref
- Yoav Kantor, Yoav Katz, Leshem Choshen, Edo Cohen-Karlik, Naftali Liberman, Assaf Toledo, Amir Menczel, and Noam Slonim. 2019. Learning to combine grammatical error corrections. In Proceedings of the Fourteenth Workshop on Innovative Use of NLP for Building Educational Applications. Florence, Italy, 139--148.Google ScholarCross Ref
- Diederik P. Kingma and Jimmy Ba. 2015. Adam: a method for stochastic optimization. In 3rd International Conf. on Learning Representations, Yoshua Bengio and Yann LeCun (Eds.). San Diego, CA, USA.Google Scholar
- Shun Kiyono, Jun Suzuki, Masato Mita, Tomoya Mizumoto, and Kentaro Inui. 2019. An empirical study of incorporating pseudo data into grammatical error correction. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). Hong Kong, China, 1236--1242.Google ScholarCross Ref
- Jared Lichtarge, Chris Alberti, and Shankar Kumar. 2020. Data Weighted Training Strategies for Grammatical Error Correction. Transactions of the Association for Computational Linguistics, Vol. 8 (2020), 634--646.Google ScholarCross Ref
- Jared Lichtarge, Chris Alberti, Shankar Kumar, Noam Shazeer, Niki Parmar, and Simon Tong. 2019. Corpora generation for grammatical error correction. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). Minneapolis, Minnesota, 3291--3301.Google ScholarCross Ref
- Mitchell P. Marcus, Beatrice Santorini, and Mary Ann Marcinkiewicz. 1993. Building a large annotated corpus of English: The Penn Treebank. Computational Linguistics, Vol. 19, 2 (1993), 313--330. Google ScholarDigital Library
- Tomoya Mizumoto, Mamoru Komachi, Masaaki Nagata, and Yuji Matsumoto. 2011. Mining revision log of language learning SNS for automated Japanese error correction of second language learners. In Proceedings of 5th International Joint Conference on Natural Language Processing. Chiang Mai, Thailand, 147--155.Google Scholar
- Courtney Napoles, Keisuke Sakaguchi, Matt Post, and Joel Tetreault. 2015. Ground truth for grammatical error correction metrics. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Vol. 2: Short Papers). Beijing, China, 588--593.Google Scholar
- Courtney Napoles, Keisuke Sakaguchi, and Joel Tetreault. 2017. JFLEG: a fluency corpus and benchmark for grammatical error Correction. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers. Valencia, Spain, 229--234.Google ScholarCross Ref
- Hwee Tou Ng, Siew Mei Wu, Ted Briscoe, Christian Hadiwinoto, Raymond Hendy Susanto, and Christopher Bryant. 2014. The CoNLL-2014 Shared Task on Grammatical Error Correction. In Proceedings of the Eighteenth Conference on Computational Natural Language Learning: Shared Task. Baltimore, MD, 1--14.Google ScholarCross Ref
- Kostiantyn Omelianchuk, Vitaliy Atrasevych, Artem Chernodub, and Oleksandr Skurzhanskyi. 2020. GECToR -- grammatical error correction: tag, not rewrite. In Proceedings of the Fifteenth Workshop on Innovative Use of NLP for Building Educational Applications. Association for Computational Linguistics, Seattle, WA, USA Online, 163--170.Google ScholarCross Ref
- Myle Ott, Sergey Edunov, Alexei Baevski, Angela Fan, Sam Gross, Nathan Ng, David Grangier, and Michael Auli. 2019. Fairseq: a fast, extensible toolkit for sequence modeling. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics (Demonstrations). Minneapolis, Minnesota, 48--53.Google ScholarCross Ref
- Keisuke Sakaguchi, Matt Post, and Benjamin Van Durme. 2017. Error-Repair dependency parsing for ungrammatical texts. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Vol. 2: Short Papers). Vancouver, Canada, 189--195.Google ScholarCross Ref
- Rico Sennrich, Barry Haddow, and Alexandra Birch. 2016a. Edinburgh neural machine translation systems for WMT 16. In Proceedings of the First Conference on Machine Translation: Volume 2, Shared Task Papers. Berlin, Germany, 371--376.Google ScholarCross Ref
- Rico Sennrich, Barry Haddow, and Alexandra Birch. 2016b. Neural machine translation of rare words with subword units. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Berlin, Germany, 1715--1725.Google ScholarCross Ref
- Noam Shazeer and Mitchell Stern. 2018. Adafactor: adaptive learning rates with sublinear memory cost. In Proceedings of the 35th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 80), Jennifer Dy and Andreas Krause (Eds.). Stockholm, Sweden, 4596--4604.Google Scholar
- Leslie N. Smith. 2015. Cyclical learning rates for training neural networks. arxiv: 1506.01186 [cs.CV]Google Scholar
- Felix Stahlberg and Shankar Kumar. 2020. Seq2Edits: Sequence Transduction Using Span-level Edit Operations. In Proceedings of the 2020conference on Empirical Methods in Natural Language Processing (EMNLP). 5147--5159.Google ScholarCross Ref
- Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Advances in neural information processing systems. Long Beach Convention Center, 5998--6008. Google ScholarDigital Library
- Ziang Xie, Guillaume Genthial, Stanley Xie, Andrew Ng, and Dan Jurafsky. 2018. Noising and denoising natural language: diverse backtranslation for grammar correction. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers). New Orleans, Louisiana, 619--628.Google ScholarCross Ref
- Helen Yannakoudakis, Øistein E Andersen, Ardeshir Geranpayeh, Ted Briscoe, and Diane Nicholls. 2018. Developing an automated writing placement system for ESL learners. Applied Measurement in Education, Vol. 31, 3 (2018), 251--267.Google ScholarCross Ref
- Zheng Yuan and Ted Briscoe. 2016. Grammatical error correction using neural machine translation. In Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. San Diego, CA, 380--386.Google ScholarCross Ref
- Wei Zhao, Liang Wang, Kewei Shen, Ruoyu Jia, and Jingming Liu. 2019. Improving grammatical error correction via pre-training a copy-augmented architecture with unlabeled data. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Vol. 1 (Long and Short Papers). Minneapolis, Minnesota, 156--165.Google ScholarCross Ref
Index Terms
- Grammatical Error Correction with Dependency Distance
Recommendations
A Comprehensive Survey of Grammatical Error Correction
Grammatical error correction (GEC) is an important application aspect of natural language processing techniques, and GEC system is a kind of very important intelligent system that has long been explored both in academic and industrial communities. The ...
Incorporating Constituent Syntax into Grammatical Error Correction with Multi-Task Learning
CIKM '23: Proceedings of the 32nd ACM International Conference on Information and Knowledge ManagementGrammatical Error Correction (GEC) is usually considered as a translation task where an erroneous sentence is treated as the source language and the corrected sentence as the target language. The state-of-the-art GEC models often adopt transformer-based ...
Incorporating rich syntax information in Grammatical Error Correction
AbstractSyntax parse trees are a method of representing sentence structure and are often used to provide models with syntax information and enhance downstream task performance. Because grammar and syntax are inherently linked, the ...
Comments