no code implementations • COLING 2022 • Ryoko Tokuhisa, Keisuke Kawano, Akihiro Nakamura, Satoshi Koide
Pre-trained language models (PLMs) such as BERT and RoBERTa have dramatically improved the performance of various natural language processing tasks.
no code implementations • COLING 2022 • Riki Fujihara, Tatsuki Kuribayashi, Kaori Abe, Ryoko Tokuhisa, Kentaro Inui
Humans use different wordings depending on the context to facilitate efficient communication.
no code implementations • 21 Feb 2024 • Yasushi Esaki, Akihiro Nakamura, Keisuke Kawano, Ryoko Tokuhisa, Takuro Kutsuna
We propose an accuracy-preserving calibration method using the Concrete distribution as the probabilistic model on the probability simplex.
1 code implementation • 2 Aug 2023 • Yunmeng Li, Jun Suzuki, Makoto Morishita, Kaori Abe, Ryoko Tokuhisa, Ana Brassard, Kentaro Inui
In this paper, we describe the development of a communication support system that detects erroneous translations to facilitate crosslingual communications due to the limitations of current machine chat translation methods.
no code implementations • 9 Mar 2023 • Keisuke Kawano, Takuro Kutsuna, Ryoko Tokuhisa, Akihiro Nakamura, Yasushi Esaki
One major challenge in machine learning applications is coping with mismatches between the datasets used in the development and those obtained in real-world applications.
no code implementations • 19 Nov 2022 • Shiki Sato, Yosuke Kishinami, Hiroaki Sugiyama, Reina Akama, Ryoko Tokuhisa, Jun Suzuki
Automation of dialogue system evaluation is a driving force for the efficient development of dialogue systems.
1 code implementation • COLING 2022 • Yosuke Kishinami, Reina Akama, Shiki Sato, Ryoko Tokuhisa, Jun Suzuki, Kentaro Inui
Prior studies addressing target-oriented conversational tasks lack a crucial notion that has been intensively studied in the context of goal-oriented artificial intelligence agents, namely, planning.
1 code implementation • SIGDIAL (ACL) 2022 • Shiki Sato, Reina Akama, Hiroki Ouchi, Ryoko Tokuhisa, Jun Suzuki, Kentaro Inui
In this scenario, the quality of the n-best list considerably affects the occurrence of contradictions because the final response is chosen from this n-best list.