Takenobu Tokunaga — accepted AI-conference papers

2024

Analyzing Interpretability of Summarization Model with Eye-gaze Information

Fariz Ikhwantri, Hiroaki Yamada, Takenobu Tokunaga

COLING 2024main

Interpretation methods provide saliency scores indicating the importance of input words for neural summarization models. Prior work has analyzed models by comparing them to human behavior, often using eye-gaze as a proxy for human attention in reading tasks such as classification. This paper present…

Cited by 0 Source ↗PDF ↗Scholar ↗

2020

Effective Use of Target-side Context for Neural Machine Translation

Hideya Mino, Hitoshi Ito, Isao Goto, Ichiro Yamada, Takenobu Tokunaga

COLING 2020main

In this paper, we deal with two problems in Japanese-English machine translation of news articles. The first problem is the quality of parallel corpora. Neural machine translation (NMT) systems suffer degraded performance when trained with noisy data. Because there is no clean Japanese-English paral…

Cited by 5 Source ↗PDF ↗code ↗Scholar ↗