Satoru Katsumata


2020

pdf bib
Cross-lingual Transfer Learning for Grammatical Error Correction
Ikumi Yamashita | Satoru Katsumata | Masahiro Kaneko | Aizhan Imankulova | Mamoru Komachi
Proceedings of the 28th International Conference on Computational Linguistics

In this study, we explore cross-lingual transfer learning in grammatical error correction (GEC) tasks. Many languages lack the resources required to train GEC models. Cross-lingual transfer learning from high-resource languages (the source models) is effective for training models of low-resource languages (the target models) for various tasks. However, in GEC tasks, the possibility of transferring grammatical knowledge (e.g., grammatical functions) across languages is not evident. Therefore, we investigate cross-lingual transfer learning methods for GEC. Our results demonstrate that transfer learning from other languages can improve the accuracy of GEC. We also demonstrate that proximity to source languages has a significant impact on the accuracy of correcting certain types of errors.

pdf bib
Grammatical Error Correction Using Pseudo Learner Corpus Considering Learner’s Error Tendency
Yujin Takahashi | Satoru Katsumata | Mamoru Komachi
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop

Recently, several studies have focused on improving the performance of grammatical error correction (GEC) tasks using pseudo data. However, a large amount of pseudo data are required to train an accurate GEC model. To address the limitations of language and computational resources, we assume that introducing pseudo errors into sentences similar to those written by the language learners is more efficient, rather than incorporating random pseudo errors into monolingual data. In this regard, we study the effect of pseudo data on GEC task performance using two approaches. First, we extract sentences that are similar to the learners’ sentences from monolingual data. Second, we generate realistic pseudo errors by considering error types that learners often make. Based on our comparative results, we observe that F0.5 scores for the Russian GEC task are significantly improved.

pdf bib
Chinese Grammatical Correction Using BERT-based Pre-trained Model
Hongfei Wang | Michiki Kurosawa | Satoru Katsumata | Mamoru Komachi
Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing

In recent years, pre-trained models have been extensively studied, and several downstream tasks have benefited from their utilization. In this study, we verify the effectiveness of two methods that incorporate a pre-trained model into an encoder-decoder model on Chinese grammatical error correction tasks. We also analyze the error type and conclude that sentence-level errors are yet to be addressed.

pdf bib
Stronger Baselines for Grammatical Error Correction Using a Pretrained Encoder-Decoder Model
Satoru Katsumata | Mamoru Komachi
Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing

Studies on grammatical error correction (GEC) have reported on the effectiveness of pretraining a Seq2Seq model with a large amount of pseudodata. However, this approach requires time-consuming pretraining of GEC because of the size of the pseudodata. In this study, we explored the utility of bidirectional and auto-regressive transformers (BART) as a generic pretrained encoder-decoder model for GEC. With the use of this generic pretrained model for GEC, the time-consuming pretraining can be eliminated. We find that monolingual and multilingual BART models achieve high performance in GEC, with one of the results being comparable to the current strong results in English GEC.

pdf bib
Automated Essay Scoring System for Nonnative Japanese Learners
Reo Hirao | Mio Arai | Hiroki Shimanaka | Satoru Katsumata | Mamoru Komachi
Proceedings of the 12th Language Resources and Evaluation Conference

In this study, we created an automated essay scoring (AES) system for nonnative Japanese learners using an essay dataset with annotations for a holistic score and multiple trait scores, including content, organization, and language scores. In particular, we developed AES systems using two different approaches: a feature-based approach and a neural-network-based approach. In the former approach, we used Japanese-specific linguistic features, including character-type features such as “kanji” and “hiragana.” In the latter approach, we used two models: a long short-term memory (LSTM) model (Hochreiter and Schmidhuber, 1997) and a bidirectional encoder representations from transformers (BERT) model (Devlin et al., 2019), which achieved the highest accuracy in various natural language processing tasks in 2018. Overall, the BERT model achieved the best root mean squared error and quadratic weighted kappa scores. In addition, we analyzed the robustness of the outputs of the BERT model. We have released and shared this system to facilitate further research on AES for Japanese as a second language learners.

2019

pdf bib
(Almost) Unsupervised Grammatical Error Correction using Synthetic Comparable Corpus
Satoru Katsumata | Mamoru Komachi
Proceedings of the Fourteenth Workshop on Innovative Use of NLP for Building Educational Applications

We introduce unsupervised techniques based on phrase-based statistical machine translation for grammatical error correction (GEC) trained on a pseudo learner corpus created by Google Translation. We verified our GEC system through experiments on a low resource track of the shared task at BEA2019. As a result, we achieved an F0.5 score of 28.31 points with the test data.

pdf bib
TMU Transformer System Using BERT for Re-ranking at BEA 2019 Grammatical Error Correction on Restricted Track
Masahiro Kaneko | Kengo Hotate | Satoru Katsumata | Mamoru Komachi
Proceedings of the Fourteenth Workshop on Innovative Use of NLP for Building Educational Applications

We introduce our system that is submitted to the restricted track of the BEA 2019 shared task on grammatical error correction1 (GEC). It is essential to select an appropriate hypothesis sentence from the candidates list generated by the GEC model. A re-ranker can evaluate the naturalness of a corrected sentence using language models trained on large corpora. On the other hand, these language models and language representations do not explicitly take into account the grammatical errors written by learners. Thus, it is not straightforward to utilize language representations trained from a large corpus, such as Bidirectional Encoder Representations from Transformers (BERT), in a form suitable for the learner’s grammatical errors. Therefore, we propose to fine-tune BERT on learner corpora with grammatical errors for re-ranking. The experimental results of the W&I+LOCNESS development dataset demonstrate that re-ranking using BERT can effectively improve the correction performance.

pdf bib
Controlling Grammatical Error Correction Using Word Edit Rate
Kengo Hotate | Masahiro Kaneko | Satoru Katsumata | Mamoru Komachi
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop

When professional English teachers correct grammatically erroneous sentences written by English learners, they use various methods. The correction method depends on how much corrections a learner requires. In this paper, we propose a method for neural grammar error correction (GEC) that can control the degree of correction. We show that it is possible to actually control the degree of GEC by using new training data annotated with word edit rate. Thereby, diverse corrected sentences is obtained from a single erroneous sentence. Moreover, compared to a GEC model that does not use information on the degree of correction, the proposed method improves correction accuracy.

2018

pdf bib
Graph-based Filtering of Out-of-Vocabulary Words for Encoder-Decoder Models
Satoru Katsumata | Yukio Matsumura | Hayahide Yamagishi | Mamoru Komachi
Proceedings of ACL 2018, Student Research Workshop

Encoder-decoder models typically only employ words that are frequently used in the training corpus because of the computational costs and/or to exclude noisy words. However, this vocabulary set may still include words that interfere with learning in encoder-decoder models. This paper proposes a method for selecting more suitable words for learning encoders by utilizing not only frequency, but also co-occurrence information, which we capture using the HITS algorithm. The proposed method is applied to two tasks: machine translation and grammatical error correction. For Japanese-to-English translation, this method achieved a BLEU score that was 0.56 points more than that of a baseline. It also outperformed the baseline method for English grammatical error correction, with an F-measure that was 1.48 points higher.

pdf bib
TMU Japanese-English Neural Machine Translation System using Generative Adversarial Network for WAT 2018
Yukio Matsumura | Satoru Katsumata | Mamoru Komachi
Proceedings of the 32nd Pacific Asia Conference on Language, Information and Computation: 5th Workshop on Asian Translation: 5th Workshop on Asian Translation