Text Simplification for Reading Assistance: A Project Note
- Kentaro Inui, Atsushi Fujita, Tetsuro Takahashi, R. Iida, Tomoya Iwakura
- LinguisticsIWP@ACL
- 11 July 2003
The issues to address to realize text simplification are discussed, the present results in three different aspects of this task are reported on: readability assessment, paraphrase representation and post-transfer error detection.
Enhancement of Encoder and Attention Using Target Monolingual Corpora in Neural Machine Translation
- Kenji Imamura, Atsushi Fujita, E. Sumita
- Computer ScienceNMT@ACL
- 1 July 2018
The experimental results show that the translation quality is improved by increasing the number of synthetic source sentences for each given target sentence, and quality close to that using a manually created parallel corpus was achieved.
Scientific Credibility of Machine Translation Research: A Meta-Evaluation of 769 Papers
- Benjamin Marie, Atsushi Fujita, Raphaël Rubino
- Computer ScienceAnnual Meeting of the Association for…
- 29 June 2021
This paper presents the first large-scale metaevaluation of machine translation (MT) conducted in 769 research papers published from 2010 to 2020 and proposes a guideline to encourage better automatic MT evaluation along with a simple meta-evaluation scoring method to assess its credibility.
Unsupervised Neural Machine Translation Initialized by Unsupervised Statistical Machine Translation
- Benjamin Marie, Atsushi Fujita
- Computer ScienceArXiv
- 30 October 2018
This work proposes to define unsupervised NMT (UNMT) as NMT trained with the supervision of synthetic bilingual data, and straightforwardly enables the use of state-of-the-art architectures proposed for supervised NMT by replacing human-made bilingual data with syntheticilingual data for training.
Tagged Back-translation Revisited: Why Does It Really Work?
- Benjamin Marie, Raphaël Rubino, Atsushi Fujita
- Computer ScienceAnnual Meeting of the Association for…
- 1 July 2020
It is concluded that the back-translations in the training data should always be tagged especially when the origin of the text to be translated is unknown, and that NMT systems trained in low-resource settings are much less vulnerable to overfit back-Translations.
Detecting Real Money Traders in MMORPG by Using Trading Network
- Atsushi Fujita, Hiroshi Itsuki, H. Matsubara
- EconomicsArtificial Intelligence and Interactive Digital…
- 9 October 2011
A method for detecting real money traders is developed to support the operators of massively multiplayer online role-playing games (MMORPGs) and shows that using the trading network is more effective in detecting RMTers than conventional machine learning methods.
Automatic Generation of Syntactically Well-formed and Semantically Appropriate Paraphrases
- Atsushi Fujita
- Computer Science
- 24 March 2005
A paraphrase generation model which consists of a case assignment rule and a handful of LCS transformation rules, with particular focus on verb alternation and compound noun decomposition is implemented, and Experimental results indicate that the model significantly outperforms conventional models.
NICT’s Unsupervised Neural and Statistical Machine Translation Systems for the WMT19 News Translation Task
- Benjamin Marie, Haipeng Sun, E. Sumita
- Computer ScienceConference on Machine Translation
- 1 August 2019
The NICT’s participation in the WMT19 unsupervised news translation task is presented, with the system ranked first for the German-to-Czech translation task, using only the data provided by the organizers (“constraint’”), according to both BLEU-cased and human evaluation.
Recurrent Stacking of Layers for Compact Neural Machine Translation Models
- Raj Dabre, Atsushi Fujita
- Computer ScienceAAAI Conference on Artificial Intelligence
- 14 July 2018
It is empirically show that the translation quality of a model that recurrently stacks a single layer 6 times is comparable to the translationquality of a models that stacks 6 separate layers.
Exploiting Multilingualism through Multistage Fine-Tuning for Low-Resource Neural Machine Translation
- Raj Dabre, Atsushi Fujita
- Computer ScienceConference on Empirical Methods in Natural…
- 1 November 2019
This paper reports on a systematic comparison of multistage fine-tuning configurations, confirming that multi-parallel corpora are extremely useful despite their scarcity and content-wise redundancy thus exhibiting the true power of multilingualism.
...
...