Papers by Atsushi Fujita
Unsupervised Extraction of Partial Translations for Neural Machine Translation (N19-1)
Copied to clipboard
| Challenge: | Neural machine translation systems usually require a large quantity of bilingual parallel data for training. |
| Approach: | They propose an algorithm for extracting from monolingual data what they call partial translations . partial translation is a pair of source and target sentences that contain sequences of tokens that are translations of each other. |
| Outcome: | The proposed algorithm extracts from monolingual data what we call partial translations . it takes only source and target monolingual datasets as input . |
Synthesizing Parallel Data of User-Generated Texts with Zero-Shot Neural Machine Translation (2020.tacl-1)
Copied to clipboard
| Challenge: | Neural machine translation systems are usually trained on clean parallel data, but the quality of translations is poor when translating noisy texts. |
| Approach: | They synthesize parallel data of UGT and exploit monolingual data to generate translations . they propose to use monolingual parallel data to train or adapt NMT systems . |
| Outcome: | The proposed approach improves the translation quality of noisy texts while making them more robust. |
Supervised and Unsupervised Machine Translation for Myanmar-English and Khmer-English (D19-52)
Copied to clipboard
Benjamin Marie, Hour Kaing, Aye Myat Mon, Chenchen Ding, Atsushi Fujita, Masao Utiyama, Eiichiro Sumita
| Challenge: | Using cleaned and normalized noisy monolingual data, supervised neural and statistical machine translation systems performed among the best for the four translation directions. |
| Approach: | They present supervised and unsupervised machine translation systems for the WAT2019 Myanmar-English and Khmer-English translation tasks. |
| Outcome: | The proposed systems performed among the best for the four translation directions. |
Coursera Corpus Mining and Multistage Fine-Tuning for Improving Lectures Translation (2020.lrec-1)
Copied to clipboard
| Challenge: | Lectures translation is a case of spoken language translation and there is nil available corpus for this purpose. |
| Approach: | They propose a framework for mining a parallel corpus from publicly available lectures at Coursera . they use machine translation and cosine similarity over continuous-space sentence representations to determine sentence alignments . |
| Outcome: | The proposed framework improves translation performance when used with out-of-domain parallel corpora . it also addresses noise in the mined data, and creates high-quality evaluation splits . |
Scientific Credibility of Machine Translation Research: A Meta-Evaluation of 769 Papers (2021.acl-long)
Copied to clipboard
| Challenge: | a meta-evaluation of machine translation (MT) has been conducted in 769 research papers . a recent study shows that evaluation practices have changed over the past decade . |
| Approach: | They propose a meta-evaluation method for machine translation that uses BLEU scores to evaluate MT performance. |
| Outcome: | The proposed meta-evaluation of machine translation shows that evaluation practices have changed over the past decade . the authors suggest that the evaluation process should be streamlined and standardized to ensure the validity of the evaluation method . |
Unsupervised Joint Training of Bilingual Word Embeddings (P19-1)
Copied to clipboard
| Challenge: | Existing methods for unsupervised bilingual word embeddings are limited by the dissimilarity between the word embedded spaces. |
| Approach: | They propose a method that trains unsupervised bilingual word embeddings jointly on parallel data generated through unsupervised machine translation. |
| Outcome: | The proposed method outperforms unsupervised mapped bilingual word embeddings in cross-lingual NLP tasks. |
Understanding Pre-Editing for Black-Box Neural Machine Translation (2021.eacl-main)
Copied to clipboard
| Challenge: | a study has demonstrated the effectiveness of pre-editing for black-box neural MT, but a deep understanding of what it is and how it works for black box NMT is lacking. |
| Approach: | They investigated 6,652 instances of pre-editing across three translation directions, two MT systems and four text domains. |
| Outcome: | The proposed method can be used in MT systems with black-box neural MT (NMT) but it is not yet fully understood in the literature. |
Tagged Back-translation Revisited: Why Does It Really Work? (2020.acl-main)
Copied to clipboard
| Challenge: | In this paper, we show that neural machine translation systems trained on large back-translated data overfit some of the characteristics of machine-transcribed texts. |
| Approach: | They propose to add a tag to back-translations to help distinguish back-translated data from original parallel training data. |
| Outcome: | The proposed tag helps the system distinguish back-translated data from original parallel training data and is as effective as a tag in high-resource training. |
Automatic Decomposition of Text Editing Examples into Primitive Edit Operations: Toward Analytic Evaluation of Editing Systems (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods to automate text editing tasks are blackboxed and do not understand the behavior of the systems. |
| Approach: | They propose a task of automatic decomposition of text editing examples into primitive edit operations by using a phrase aligner and a large language model. |
| Outcome: | The proposed method perfectly decomposes 44% and 64% of editing examples . Detailed analyses also provide insights into the difficulties of this task . |
Exploiting Multilingualism through Multistage Fine-Tuning for Low-Resource Neural Machine Translation (D19-1)
Copied to clipboard
| Challenge: | Using multi-parallel corpora for transfer learning is a useful technique for low-resource NMT. |
| Approach: | They compare multi-parallel corpora for transfer learning in a low-resource setting . their results show that multi-paralleled corpors are extremely useful . |
| Outcome: | The proposed model can give 3–9 BLEU score gains over a one-to-one model. |