Aussie AI
Grammatical Error Correction
-
Last Updated 7 December, 2024
-
by David Spuler, Ph.D.
Grammatical Error Correction (GEC) is the research term for correcting errors in written text. The everyday terms are words like "editing" and "proofreading."
GEC research aims to use computers, especially LLMs and Transformers, to automatically proofread and correct written text. Modern Transformers have been used to perform GEC tasks since the earliest days of Transformers in 2017.
Use cases for GEC include:
- Proofreading documents (i.e., revisions, copy editing, etc.)
- Autocorrect
- Language learning instructions (i.e. teaching English to weaker speakers, such as children or non-English speaking adults).
LLMs for Grammar Correction
The use of LLMs for GEC has been a mixed success. They are technically strong at finding errors, but have a tendency to "over-correct" and are also slow and inefficient to run. Overall, in the literature, although LLMs are popular in GEC papers, some of the non-LLM methods are still regarded as "state-of-the-art" rather than the use of LLMs like ChatGPT.
Pros. On the positive side, a strong LLM like ChatGPT can do a lot of things well:
- Grammatical corrections. It can fix a lot of basic spelling and grammatical errors.
- Advanced improvements. LLMs can make many advanced edits for fluency and creativity. The ability of an LLM to output fluent, grammatically correct English is one of their strengths.
- Multilingual corrections. Another strength is that this capabiity exists in many languages, not only English, as several of the top models are multilingual.
Cons. On the downside, the problems include:
- Over-correction: tendency to make major changes for fluency or creativity, rather than a minimal set of edits for correctness. Having too many corrections made on a document can be discouraging for teaching young children or non-English speakers. For example, correcting a phrase to a more eloquent way of writing is not helpful for these audiences.
- Inefficiency. A large LLM is required for accuracy (e.g. GPT), but this is running a lot of GPU commands behind-the-scenes. This is usually worked-around by sending the request over the network to an LLM engine running in the cloud.
- Many tokens. Correction of written text requires a large number of tokens, twice. The original document is the input text, and it must be "encoded" by GPU (or via "prefill"). Then the answer also has about the same number of words, so it is also a long response, requiring lots of computation. So it can be doubly inefficient in terms of cost and GPU processing requirements.
- Stateless. LLMs operate in a stateless manner, requiring the context re-analyzed for every query. Hence, running an "autocorrect" via an LLM with a Transformer engine will require re-analysis by the LLM for every keystroke, or at least for every word typed, which further increases the number of tokens and the GPU power required.
- On-device GEC difficult. Because of the inefficiency and many-tokens problems, trying to run an LLM locally on a phone, PC/laptop, or other low-resource device is difficult. For example, the "autocorrect" on your iPhone while you type a text is certainly not running an LLM in the background.
Research on LLM GEC: Research papers on using LLMs for GEC:
- Robert Östling, Katarina Gillholm, Murathan Kurfalı, Marie Mattson, Mats Wirén, 17 Aug 2023, Evaluation of really good grammatical error correction, https://arxiv.org/abs/2308.08982 (Examines GPT-3 use in GEC and finds it effective.)
- Maria Carolina Penteado, Fábio Perez, 18 Jul 2023 (v2), Evaluating GPT-3.5 and GPT-4 on Grammatical Error Correction for Brazilian Portuguese, https://arxiv.org/abs/2306.15788
- Yinghui Li, Shang Qin, Jingheng Ye, Shirong Ma, Yangning Li, Libo Qin, Xuming Hu, Wenhao Jiang, Hai-Tao Zheng, Philip S. Yu, 18 Feb 2024, Rethinking the Roles of Large Language Models in Chinese Grammatical Error Correction, https://arxiv.org/abs/2402.11420
- Masamune Kobayashi, Masato Mita, Mamoru Komachi, 26 Mar 2024, Large Language Models Are State-of-the-Art Evaluator for Grammatical Error Correction, https://arxiv.org/abs/2403.17540
- 24 Feb 2024, Evaluating Prompting Strategies for Grammatical Error Correction Based on Language Proficiency, Min Zeng, Jiexin Kuang, Mengyang Qiu, Jayoung Song, Jungyeul Park, https://arxiv.org/abs/2402.15930
- Steven Coyne, Keisuke Sakaguchi, Diana Galvan-Sosa, Michael Zock, Kentaro Inui, 30 May 2023 (v2), Analyzing the Performance of GPT-3.5 and GPT-4 in Grammatical Error Correction, https://arxiv.org/abs/2303.14342
- Haoran Wu, Wenxuan Wang, Yuxuan Wan, Wenxiang Jiao, and Michael Lyu. 2023. ChatGPT or Grammarly? Evaluating ChatGPT on grammatical error correction benchmark. arXiv:2303.13648. https://arxiv.org/abs/2303.13648
- Jared Lichtarge, Christopher Alberti, Shankar Kumar, Noam Shazeer, and Niki Parmar. 2018. Weakly supervised grammatical error correction using iterative decoding. CoRR, abs/1811.01710. https://arxiv.org/abs/1811.01710 (Beam search decoding with a high threshold to emit corrections.)
- Jindrich Libovicky, Jindrich Helcl, Marek Tlusty, Ondrej Bojar, and Pavel Pecina. 2016. CUNI system for WMT16 automatic post-editing and multimodal translation tasks. In Proceedings of the First Conference on Machine Translation: Volume 2, Shared Task Papers, pages 646–654, Berlin, Germany. https://arxiv.org/abs/1606.07481 (Post-editing of machine translation.)
- Alexandre Berard, Laurent Besacier, Olivier Pietquin. 2017. LIG-CRIStAL submission for the WMT2017automatic post-editing task. In Proceed ings of the Second Conference on Machine Transla tion, pages 623–629, Copenhagen, Denmark. Asso ciation for Computational Linguistics. https://aclanthology.org/W17-4772.pdf (Post-editing of machine translation using a simpler method that should be closer to spelling correction.)
- Sergiu Nisioi, Sanja Stajner, Simone Paolo Ponzetto, and Liviu P Dinu. 2017. Exploring neural text simplification models. In Proceedings of the 55th An nual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 85–91. https://aclanthology.org/P17-2014/ PDF: https://aclanthology.org/P17-2014.pdf (Text simplification.)
- Abigail See, Peter J. Liu, and Christopher D. Manning. 2017. Get to the point: Summarization with pointer generator networks. In Proceedings of the 55th An nual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1073 1083, Vancouver, Canada. Association for Computa tional Linguistics. https://arxiv.org/abs/1704.04368 https://aclanthology.org/P17-1099/ (Text summarization.)
- Jiwei Tan, Xiaojun Wan, and Jianguo Xiao. 2017. Abstractive document summarization with a graph based attentional neural model. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1171–1181. https://aclanthology.org/P17-1108/ PDF: https://aclanthology.org/P17-1108.pdf
- Marcin Junczys-Dowmunt, Roman Grundkiewicz, Shubha Guha, and Kenneth Heafield. 2018. Approaching neural grammatical error correction as a low-resource machine translation task. Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pages 595–606, New Orleans, Louisiana. https://aclanthology.org/N18-1055/ PDF: https://aclanthology.org/N18-1055.pdf
- Ottokar Tilk and Tanel Alum¨ae. 2016. Bidirectional recurrent neural network with attention mechanism for punctuation restoration. In Interspeech, pages 3047–3051. PDF: https://www.researchgate.net/profile/Ottokar-Tilk/publication/307889284_Bidirectional_Recurrent_Neural_Network_with_Attention_Mechanism_for_Punctuation_Restoration/links/57ed346708ae26b51b395be1/Bidirectional-Recurrent-Neural-Network-with-Attention-Mechanism-for-Punctuation-Restoration.pdf
- 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: Hu man Language Technologies, Volume 1 (Long and Short Papers), pages 156–165, Minneapolis, Min nesota. https://arxiv.org/abs/1903.00138 https://aclanthology.org/N19-1014/
- Ning Shi, Ziheng Zeng, Haotian Zhang, Yichen Gong, 30 Sep 2020 (v2), Recurrent Inference in Text Editing, https://arxiv.org/abs/2009.12643
- Yiwei Wang, Muhao Chen, Nanyun Peng, Kai-Wei Chang, 1 Apr 2024 (v2), DeepEdit: Knowledge Editing as Decoding with Constraints, https://arxiv.org/abs/2401.10471
- Kostiantyn Omelianchuk, Vitaliy Atrasevych, Artem Chernodub, Oleksandr Skurzhanskyi, 29 May 2020 (v2), GECToR -- Grammatical Error Correction: Tag, Not Rewrite, https://arxiv.org/abs/2005.12592 (GEC using the encoder of a Transformer.)
- Dimitrios Alikaniotis, Vipul Raheja, 4 Jun 2019, The Unreasonable Effectiveness of Transformer Language Models in Grammatical Error Correction, https://arxiv.org/abs/1906.01733 (Examines BERT, GPT and GPT-2 Transformers using a simple decoding method with a threshold to decide when to make an edit.)
- Tao Fang, Shu Yang, Kaixin Lan, Derek F. Wong, Jinpeng Hu, Lidia S. Chao, Yue Zhang, 4 Apr 2023, Is ChatGPT a Highly Fluent Grammatical Error Correction System? A Comprehensive Evaluation, https://arxiv.org/abs/2304.01746
- Mengsay Loem, Masahiro Kaneko, Sho Takase, and Naoaki Okazaki. 2023. Exploring effectiveness of GPT-3 in grammatical error correction: A study on performance and controllability in prompt-based methods. In Proceedings of the 18th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2023), pages 205–219, Toronto, Canada. Association for Computational Linguistics https://aclanthology.org/2023.bea-1.18/
- 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, pages 252–263, Florence, Italy. Association for Computational Linguistics. https://aclanthology.org/W19-4427/
- Michihiro Yasunaga, Jure Leskovec, and Percy Liang. 2021. LM-Critic: language models for unsupervised grammatical error correction. arXiv:2109.06822. https://arxiv.org/abs/2109.06822 https://aclanthology.org/2021.emnlp-main.611/
Edit Decoding
Many of the LLM GEC approaches do not change the decoding algorithm used in editing, but rely on prompt engineering using the default decoding algorithms (e.g. greedy, top-k, top-p, beam, etc.). This is inherently inefficient because it does not specialize the decoding algorithm to the GEC use case, and thereby wastes an opportunity to go faster.
However, there are ways to modify the decoding algorithm called "Edit decoding". The idea is to process the token "logits" in a way that understands the process is to do editing, rather than elongation or "completion" of the prompt.
For research papers on "edit decoding" ideas, see edit decoding research.
Aggressive Decoding
Aggressive decoding is an optimization that runs decoding in parallel, using the original input text as a kind of lookahead template. It can speed up latency and response time for a user, at the cost of additional GPU computation in parallel. Hence, it is a candidate for speeding up GEC in a large data center with many GPUs available, but not for on-device inference on resource-contrained edge devices like phones or PCs.
See research on aggressive decoding.
General Research Papers on Grammatical Error Correction (GEC)
Much of the research on Grammatical Error Correction (GEC) is not using edit decoding or aggressive decoding, but involves training an edit-specific model. The Seq2Edit approach involves training a model on a data set specific to editing actions (e.g. insert, delete, keep) and then running a BERT-like encoder-only model efficiently on input texts to perform editing.
- Kostiantyn Omelianchuk, Vitaliy Atrasevych, Artem Chernodub, and Oleksandr Skurzhanskyi. 2020. GECToR – grammatical error correction: Tag, not rewrite. Proceedings of BEA. https://arxiv.org/abs/2005.12592 (Grammarly research paper on using a BERT-like encoder-only model training on grammatical correction training data in order to tag token sequences for common edits such as keep/delete/correct which mean things like reject the current token or correct to insert a new token.)
- Y Zhang, Y Zhang, L Cui, G Fu, Oct 2023, Non-autoregressive Text Editing with Copy-aware Latent Alignments, arXiv preprint arXiv:2310.07821, https://arxiv.org/pdf/2310.07821.pdf (Seq2Edit method of more efficiently using an encoder-only model for generating edit actions for a text.)
- Zewei Zhao, Houfeng Wang, April 2020, MaskGEC: Improving Neural Grammatical Error Correction via Dynamic Masking, Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 34, No. 01, AAAI-20 ,Technical Tracks 1, DOI: https://doi.org/10.1609/aaai.v34i01.5476, https://ojs.aaai.org/index.php/AAAI/article/view/5476
- Michihiro Yasunaga, Jure Leskovec, Percy Liang, 8 Oct 2021 (v2), LM-Critic: Language Models for Unsupervised Grammatical Error Correction, https://arxiv.org/abs/2109.06822, Code: https://github.com/michiyasunaga/LM-Critic
- Gustavo Sutter Pessurno de Carvalho, 2024, Multilingual Grammatical Error Detection And Its Applications to Prompt-Based Correction, https://uwspace.uwaterloo.ca/handle/10012/20216, http://hdl.handle.net/10012/20216
- Agnes Luhtaru, Taido Purason, Martin Vainikko, Maksym Del, Mark Fishel, 8 Mar 2024, To Err Is Human, but Llamas Can Learn It Too, https://arxiv.org/abs/2403.05493 (Intentionally fine-tuning LLMs to make grammatical errors, so as to create synthetic data to train better GEC models.)
- Chenming Tang, Fanyi Qu, Yunfang Wu, 28 Mar 2024, Ungrammatical-syntax-based In-context Example Selection for Grammatical Error Correction, https://arxiv.org/abs/2403.19283 (Syntax tree comparison for GEC.)
- Abhijeet Awasthi, Sunita Sarawagi, Rasna Goyal, Sabyasachi Ghosh, Vihari Piratla, 15 May 2020 (v2), Parallel Iterative Edit Models for Local Sequence Transduction, https://arxiv.org/abs/1910.02893 (Transforms the input text into a sequence of edits and then does parallel optimizations.)
- Marcin Junczys-Dowmunt, Roman Grundkiewicz, Shubha Guha, and Kenneth Heafield. 2018. Approaching neural grammatical error correction as a low-resource machine translation task. Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pages 595–606, New Orleans, Louisiana. https://aclanthology.org/N18-1055/, PDF: https://aclanthology.org/N18-1055.pdf
- Ottokar Tilk and Tanel Alumae. 2016. Bidirectional recurrent neural network with attention mechanism for punctuation restoration. In Interspeech, pages 3047–3051. PDF: https://www.researchgate.net/profile/Ottokar-Tilk/publication/307889284_Bidirectional_Recurrent_Neural_Network_with_Attention_Mechanism_for_Punctuation_Restoration/links/57ed346708ae26b51b395be1/Bidirectional-Recurrent-Neural-Network-with-Attention-Mechanism-for-Punctuation-Restoration.pdf
- Wei Zhao, Liang Wang, Kewei Shen, Ruoyu Jia, 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, Volume 1 (Long and Short Papers), pages 156–165, Minneapolis, Minnesota. https://arxiv.org/abs/1903.00138, https://aclanthology.org/N19-1014/
- Jiwei Tan, Xiaojun Wan, and Jianguo Xiao. 2017. Abstractive document summarization with a graph based attentional neural model. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1171–1181. https://aclanthology.org/P17-1108/, PDF: https://aclanthology.org/P17-1108.pdf
- Abigail See, Peter J. Liu, and Christopher D. Manning. 2017. Get to the point: Summarization with pointer generator networks. In Proceedings of the 55th An nual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1073 1083, Vancouver, Canada. Association for Computa tional Linguistics. https://arxiv.org/abs/1704.04368, https://aclanthology.org/P17-1099/ (Text summarization.)
- Sergiu Nisioi, Sanja Stajner, Simone Paolo Ponzetto, and Liviu P Dinu. 2017. Exploring neural text simplification models. In Proceedings of the 55th An nual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 85–91. https://aclanthology.org/P17-2014/, PDF: https://aclanthology.org/P17-2014.pdf (Text simplification.)
- Alexandre Berard, Laurent Besacier, Olivier Pietquin. 2017. LIG-CRIStAL submission for the WMT2017automatic post-editing task. In Proceed ings of the Second Conference on Machine Transla tion, pages 623–629, Copenhagen, Denmark. Asso ciation for Computational Linguistics. https://aclanthology.org/W17-4772.pdf (Post-editing of machine translation using a simpler method that should be closer to spelling correction.)
- Jindrich Libovicky, Jindrich Helcl, Marek Tlusty, Ondrej Bojar, Pavel Pecina. 2016. CUNI system for WMT16 automatic post-editing and multimodal translation tasks. In Proceedings of the First Con ference on Machine Translation: Volume 2, Shared Task Papers, pages 646–654, Berlin, Germany. https://arxiv.org/abs/1606.07481 (Post-editing of machine translation.)
- Sascha Rothe, Jonathan Mallinson, Eric Malmi, Sebas tian Krause, and Aliaksei Severyn. 2021. A simple recipe for multilingual grammatical error correction. In Proceedings of the 59th Annual Meet ing of the Association for Computational Linguistics https://aclanthology.org/2021.acl-short.89/ PDF: https://aclanthology.org/2021.acl-short.89.pdf (Regarded as the SOTA Seq2Seq GEC model.)
- Qiao Wang, Zheng Yuan, June 7th, 2024, Sequence Tagging Approach in Grammar Error Detection: Identifying Areas of Improvement for the State-of-the-Art, DOI: https://doi.org/10.21203/rs.3.rs-4479362/v1 PDF: https://assets-eu.researchsquare.com/files/rs-4479362/v1_covered_43b09539-8126-4084-afeb-ed41ae4c905e.pdf?c=1717734544
- António V. Lopes, M. Amin Farajian, Gonçalo M. Correia, Jonay Trenous, André F. T. Martins, 29 Jun 2019 (v2), Unbabel's Submission to the WMT2019 APE Shared Task: BERT-based Encoder-Decoder for Automatic Post-Editing, https://arxiv.org/abs/1905.13068
- Anisia Katinskaia, Roman Yangarber, July 2023, Grammatical Error Correction for Sentence-level Assessment in Language Learning, Proceedings of the 18th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2023), Association for Computational Linguistics, Toronto, Canada, https://aclanthology.org/2023.bea-1.41/
- Masato Mita, Keisuke Sakaguchi, Masato Hagiwara, Tomoya Mizumoto, Jun Suzuki, Kentaro Inui, 23 May 2022, Towards Automated Document Revision: Grammatical Error Correction, Fluency Edits, and Beyond, https://arxiv.org/abs/2205.11484
- William Castillo-González, Carlos Oscar Lepez, Mabel Cecilia Bonardi, 22 December, 2022, Chat GPT: a promising tool for academic editing, https://dm.saludcyt.ar/index.php/dm/article/view/23 https://www.researchgate.net/publication/373185669_Chat_GPT_a_promising_tool_for_academic_editing (Using ChatGPT for editing and proofreading of scientific writing.)
- Vipul Raheja, Dhruv Kumar, Ryan Koo, Dongyeop Kang, 23 Oct 2023 (v2), CoEdIT: Text Editing by Task-Specific Instruction Tuning, https://arxiv.org/abs/2305.09857 (Trained a new model that does well on editing and other revision tasks.)
- Francisco Ribeiro, José Nuno Castro de Macedo, Kanae Tsushima, Rui Abreu, João Saraiva, 2023, GPT-3-Powered Type Error Debugging: Investigating the Use of Large Language Models for Code Repair, SLE 2023: Proceedings of the 16th ACM SIGPLAN International Conference on Software Language Engineering, October 2023, Pages 111–124, https://doi.org/10.1145/3623476.3623522 (Code corrections are a type of GEC.)
- Boris Almonacid, 9 May 2023, Towards an Automatic Optimisation Model Generator Assisted with Generative Pre-trained Transformer, https://arxiv.org/abs/2305.05811 (Uses OpenAI's "text-davinci-edit-001" model for editing.)
- Milton Pividori and Casey S. Greene, 2023, A publishing infrastructure for AI-assisted academic authoring, doi: 10.1101/2023.01.21.525030, https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9900745/ (Uses OpenAI edit model "text-davinci-edit-001" was evaluated but not useed for editing parts of the process.)
- Christopher Davis, Andrew Caines, Øistein Andersen, Shiva Taslimipoor, Helen Yannakoudakis, Zheng Yuan, Christopher Bryant, Marek Rei, Paula Buttery, 15 Jan 2024, Prompting open-source and commercial language models for grammatical error correction of English learner text, https://arxiv.org/abs/2401.07702
- Jared Lichtarge, Christopher Alberti, Shankar Kumar, Noam Shazeer, and Niki Parmar. 2018. Weakly supervised grammatical error correction using iterative decoding. CoRR, abs/1811.01710. https://arxiv.org/abs/1811.01710 (Beam search decoding with a high threshold to emit corrections.)
- R Grundkiewicz, 2019, Minimally-augmented grammatical error correction, Proceedings of the 2019 EMNLP Workshop W-NUT: The 5th Workshop on Noisy User-generated Text, pages 357–363, Hong Kong, Nov 4, 2019., https://aclanthology.org/D19-5546.pdf
- S Xu, J Zhang, J Chen, L Qin, 2019, Erroneous data generation for grammatical error correction, Proceedings of the Fourteenth Workshop on Innovative Use of NLP for Building Educational Applications, pages 149–158, Florence, Italy, August 2, 2019, https://aclanthology.org/W19-4415.pdf
- Daniel Dahlmeier, Hwee Tou Ng, 2012, A Beam-Search Decoder for Grammatical Error Correction, Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, pages 568–578, Jeju Island, Korea, 12–14 July 2012, https://aclanthology.org/D12-1052.pdf
- Weijia Xu, Marine Carpuat, March 31 2021, EDITOR: An Edit-Based Transformer with Repositioning for Neural Machine Translation with Soft Lexical Constraints, Transactions of the Association for Computational Linguistics (2021) 9: 311–328, https://doi.org/10.1162/tacl_a_00368 https://direct.mit.edu/tacl/article/doi/10.1162/tacl_a_00368/98622/EDITOR-An-Edit-Based-Transformer-with
- Deifilia To, Feb 14, 2023, Using OpenAI’s editing model to edit a Microsoft Word document, https://medium.com/@deifilia.to/using-openais-editing-model-to-edit-a-microsoft-word-document-26c001ad7e40
- OpenAI Staff, March 2022, Introducing Insert and Edits Capabilities, OpenAI Developer Forum, https://community.openai.com/t/introducing-insert-and-edits-capabilities/15993
- Mohammad Bavarian, Angela Jiang, Heewoo Jun, Henrique Pondé, OpenAI, March 15, 2022, New GPT-3 capabilities: Edit & insert, Open AI Blog, https://openai.com/blog/gpt-3-edit-insert
- Jared Lichtarge, Chris Alberti, Shankar Kumar, Noam Shazeer, Niki Parmar, Simon Tong, 10 Apr 2019, Corpora Generation for Grammatical Error Correction, https://arxiv.org/abs/1904.05780
- C Park, S Koo, G Kim, H Lim , 2024, Towards Harnessing the Most of ChatGPT for Korean Grammatical Error Correction, Applied Sciences, https://www.mdpi.com/2076-3417/14/8/3195
- Yu Wang, Yuelin Wang, Kai Dang, Jie Liu, Zhuo Liu, 20 December 2021, A Comprehensive Survey of Grammatical Error Correction, ACM Transactions on Intelligent Systems and Technology, Volume 12, Issue 5, Article No.: 65, pp 1–51, https://doi.org/10.1145/3474840 https://dl.acm.org/doi/abs/10.1145/3474840
- Yu Wang, Yuelin Wang, Jie Liu, Zhuo Liu, 2 May 2020, A Comprehensive Survey of Grammar Error Correction, https://arxiv.org/abs/2005.06600
- Alexey Sorokin, December 2022, Improved grammatical error correction by ranking elementary edits, Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, Abu Dhabi, United Arab Emirates, PDF: https://aclanthology.org/2022.emnlp-main.785.pdf
- Wei Li, Houfeng Wang, 28 May 2024, Detection-Correction Structure via General Language Model for Grammatical Error Correction, https://arxiv.org/abs/2405.17804
- Renjie Liu, Yanxiang Zhang, Yun Zhu, Haicheng Sun, Yuanbo Zhang, Michael Xuelin Huang, Shanqing Cai, Lei Meng, Shumin Zhai, 6 Jun 2024, Proofread: Fixes All Errors with One Tap https://arxiv.org/abs/2406.04523 Demo: https://www.youtube.com/watch?v=4ZdcuiwFU7I
- Bohdan Didenko, Andrii Sameliuk, 19 Sep 2023, RedPenNet for Grammatical Error Correction: Outputs to Tokens, Attentions to Spans, https://arxiv.org/abs/2309.10898
- Jean Kaddour, Joshua Harris, Maximilian Mozes, Herbie Bradley, Roberta Raileanu, Robert McHardy, 19 Jul 2023, Challenges and Applications of Large Language Models, https://arxiv.org/abs/2307.10169
- Rohit Raju, Peeta Basa Pati, SA Gandheesh, Gayatri Sanjana Sannala, Suriya KS, 25 Mar 2024, Grammatical vs Spelling Error Correction: An Investigation into the Responsiveness of Transformer-based Language Models using BART and MarianMT, https://www.worldscientific.com/doi/abs/10.1142/S0219649224500370 (Analysis of the effectiveness of detecting grammar errors using two models.)
- Masamune Kobayashi, Masato Mita, Mamoru Komachi, 5 Mar 2024] Revisiting Meta-eva,uation for Grammatical Error Correction, https://arxiv.org/abs/2403.02674 (Proposes a new training data set for grammar corrections.)
- Jiahao Wang, Guimin Huang, Yabing Wang, 2023, An Automatic Grammar Error Correction Model Based on Encoder-decoder Structure for English Texts, EAI Endorsed Transactions on Scalable Information Systems, Vol. 10 ,No. 1, (2023), https://publications.eai.eu/index.php/sis/article/view/2011 (Dual encoder architecture that analyzes the input and context sentences separately.)
- Yue Zhang, Bo Zhang, Zhenghua Li, Zuyi Bao, Chen Li, Min Zhang, 22 Oct 2022, SynGEC: Syntax-Enhanced Grammatical Error Correction with a Tailored GEC-Oriented Parser, https://arxiv.org/abs/2210.12484 Code: https://github.com/HillZhang1999/SynGEC (Merge a tree-structured parser used as a syntactic model with the encoder part of a Transformer.)
- Masahiro Kaneko, Masato Mita, Shun Kiyono, Jun Suzuki, Kentaro Inui, 31 May 2020 (v2), Encoder-Decoder Models Can Benefit from Pre-trained Masked Language Models in Grammatical Error Correction, Code: https://github.com/kanekomasahiro/bert-gec (Incorporting a BERT encoder-only model into the use of an encoder-decoder model in editing.)
- Shamil Chollampatt, Weiqi Wang, and Hwee Tou Ng, July 2019, Cross-Sentence Grammatical Error Correction, P19-1042, Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, https://aclanthology.org/P19-1042/ PDF: https://aclanthology.org/P19-1042.pdf (Doing more complicated editing corrections across multiple sentences and longer texts.)
- Sina Ahmadi, 21 Sep 2018, Attention-based Encoder-Decoder Networks for Spelling and Grammatical Error Correction, https://arxiv.org/abs/1810.00660 (Early paper on use of encoder-decoder architectures in GEC/editing.)
- Jano le Roux, June 2024, Apple Just Completely Wrecked Grammarly with Apple Intelligence, https://medium.com/swlh/apple-just-completely-wrecked-grammarly-with-apple-intelligence-ea9bdc27c317
- H Wu, W Wang, Y Wan, W Jiao, M Lyu, 2023, Chatgpt or grammarly? evaluating chatgpt on grammatical error correction benchmark, https://arxiv.org/abs/2303.13648
- T Fang, S Yang, K Lan, DF Wong, J Hu, 2023, Is chatgpt a highly fluent grammatical error correction system? a comprehensive evaluation, https://arxiv.org/abs/2304.01746
- R Schmidt-Fajlik, 2023, ChatGPT as a Grammar Checker for Japanese English Language Learners: A Comparison with Grammarly and ProWritingAid, https://asiacall-acoj.org/index.php/journal/article/download/29/16
- D Astuti, D Darmahusni, S Sumarni, 2023, The Use of Grammarly in the Academic Writing of Undergraduate Students: Advantages, Weaknesses, and Challenges (Systematic Review), https://jurnal.unimus.ac.id/index.php/ELLIC/article/download/12570/7152
- Jonathan Mallinson, Jakub Adamek, Eric Malmi, Aliaksei Severyn, Oct 2022, EdiT5: Semi-Autoregressive Text-Editing with T5 Warm-Start, https://arxiv.org/abs/2205.12209
- Yisheng Xiao, Lijun Wu, Junliang Guo, Juntao Li, Min Zhang, Tao Qin, Tie-yan Liu, 6 Jul 2023 (v2), A Survey on Non-Autoregressive Generation for Neural Machine Translation and Beyond, https://arxiv.org/pdf/2204.09269.pdf
- Zhenghao Liu, Xiaoyuan Yi, Maosong Sun, Liner Yang, and Tat-Seng Chua. 2021. Neural quality estimation with multiple hypotheses for grammatical error correction. arXiv:2105.04443. https://arxiv.org/abs/2105.04443 https://aclanthology.org/2021.naacl-main.429/
- Mengsay Loem, Masahiro Kaneko, Sho Takase, and Naoaki Okazaki. 2023. Exploring effectiveness of GPT-3 in grammatical error correction: A study on performance and controllability in prompt-based methods. In Proceedings of the 18th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2023), pages 205–219, Toronto, Canada. Association for Computational Linguistics https://aclanthology.org/2023.bea-1.18/
- 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, pages 252–263, Florence, Italy. Association for Computational Linguistics. https://aclanthology.org/W19-4427/
- Steven Coyne, Keisuke Sakaguchi, Diana Galvan-Sosa, Michael Zock, and Kentaro Inui. 2023. Analyzing the performance of GPT-3.5 and GPT-4 in Grammatical Error Correction. arXiv:2303.14342 https://arxiv.org/abs/2303.14342
- Sabrina Ortiz, June 25, 2024, Grammarly adds 5 new security and control features for enterprise users, https://www.zdnet.com/home-and-office/work-life/grammarly-adds-5-new-security-and-control-features-for-enterprise-users/
- Oleksandr Korniienko, 2024, Enhancing Grammatical Correctness: The Efficacy of Large Language Models in Error Correction Task, Masters Thesis, Department of Computer Sciences, Faculty of Applied Sciences, Ukrainian Catholic University, Lviv, Ukraine, https://er.ucu.edu.ua/bitstream/handle/1/4669/korniienko.pdf?sequence=1
- Dingyi Yang, Qin Jin, 26 Aug 2024, What Makes a Good Story and How Can We Measure It? A Comprehensive Survey of Story Evaluation, https://arxiv.org/abs/2408.14622
- Yinghao Li, Xuebo Liu, Shuo Wang, Peiyuan Gong, Derek F. Wong, Yang Gao, Heyan Huang, and Min Zhang. 2023. TemplateGEC: Improving Grammatical Error Correction with Detection Template. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 6878–6892, Toronto, Canada. Association for Computational Linguistics. https://aclanthology.org/2023.acl-long.380/ https://aclanthology.org/2023.acl-long.380.pdf
- Asif Razzaq, September 5, 2024, Yi-Coder Released by 01.AI: A Powerful Small-Scale Code LLM Series, Delivering Exceptional Performance in Code Generation, Editing, and Long-Context Comprehension, https://www.marktechpost.com/2024/09/05/yi-coder-released-by-01-ai-a-powerful-small-scale-code-llm-series-delivering-exceptional-performance-in-code-generation-editing-and-long-context-comprehension/
- X Wang, L Mu, J Zhang, H Xu, 2024, Multi-pass Decoding for Grammatical Error Correction, Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 9904–9916, November 12-16, 2024, https://aclanthology.org/2024.emnlp-main.553.pdf
- Shwetha Somasundaram, Anirudh Phukan, Apoorv Saxena, 2 Dec 2024, PLD+: Accelerating LLM inference by leveraging Language Model Artifacts, https://arxiv.org/abs/2412.01447
More AI Research
Read more about: