Papers by Satoru Katsumata
Stronger Baselines for Grammatical Error Correction Using a Pretrained Encoder-Decoder Model (2020.aacl-main)
Copied to clipboard
| Challenge: | Strong pretraining approaches for grammatical error correction require extensive use of a pseudo-parallel corpus. |
| Approach: | They propose to use bidirectional and auto-regressive transformers as a generic pretrained encoder-decoder model for grammatical error correction (GEC) they 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. |
| Outcome: | The proposed model achieves comparable results to the current strong results in English GEC. |
Chinese Grammatical Correction Using BERT-based Pre-trained Model (2020.aacl-main)
Copied to clipboard
| Challenge: | Recent studies have shown that pre-trained models improve performance on downstream tasks. |
| Approach: | They propose to incorporate a pre-trained model into an encoder-decoder model to improve the performance of Chinese grammatical error correction tasks. |
| Outcome: | The proposed method improves the performance of Chinese grammatical error correction tasks. |
Automated Essay Scoring System for Nonnative Japanese Learners (2020.lrec-1)
Copied to clipboard
| Challenge: | Existing systems only provide a holistic score that summarizes the quality of an essay, which provides little feedback for a language learner. |
| Approach: | They developed an automated essay scoring system for Japanese as a second language learners using an essay dataset with annotations for a holistic score and multiple trait scores. |
| Outcome: | The proposed system achieves the highest accuracy in various natural language processing tasks. |
Graph-based Filtering of Out-of-Vocabulary Words for Encoder-Decoder Models (P18-3)
Copied to clipboard
| Challenge: | Encoder-decoder models employ words that are frequently used in the training corpus but may still include noisy words. |
| Approach: | They propose a method for selecting more suitable words for learning encoders by utilizing co-occurrence information. |
| Outcome: | The proposed method outperforms the baseline method in Japanese-to-English translation and grammatical error correction tasks with an F-measure of 1.48 points higher. |
Controlling Grammatical Error Correction Using Word Edit Rate (P19-2)
Copied to clipboard
| Challenge: | Existing models for grammatical error correction only consider the single degree of correction suited for training corpus. |
| Approach: | They propose a neural grammar error correction method that can control the degree of correction by using new training data annotated with word edit rate. |
| Outcome: | The proposed method improves correction accuracy by using training data annotated with word edit rate. |
Grammatical Error Correction Using Pseudo Learner Corpus Considering Learner’s Error Tendency (2020.acl-srw)
Copied to clipboard
| Challenge: | Recent studies have focused on improving the performance of grammatical error correction (GEC) tasks using pseudo data. |
| Approach: | They propose to extract sentences similar to those written by language learners and generate pseudo errors by considering error types that learners often make. |
| Outcome: | The proposed model significantly improves the performance of the Russian GEC task compared with other models using pseudo data. |
Cross-lingual Transfer Learning for Grammatical Error Correction (2020.coling-main)
Copied to clipboard
| Challenge: | Existing studies on English GEC have focused on improving it, but the resources required to train the models are not sufficient. |
| Approach: | They investigate cross-lingual transfer learning in grammatical error correction tasks . similarities between these languages is a key factor for successfully transferring grammatikal knowledge . |
| Outcome: | The proposed methods improve accuracy of grammatical error correction tasks in English and Russian, but lack the resources to train models in these languages. |