1 code implementation • Findings (EMNLP) 2021 • Junya Takayama, Tomoyuki Kajiwara, Yuki Arase
We create a large-scale dialogue corpus that provides pragmatic paraphrases to advance technology for understanding the underlying intentions of users.
1 code implementation • 21 Jun 2022 • Yuya Sasaki, Junya Takayama, Juan Ramón Santana, Shohei Yamasaki, Tomoya Okuno, Makoto Onizuka
Nowadays, so as to improve services and urban areas livability, multiple smart city initiatives are being carried out throughout the world.
1 code implementation • ACL 2021 • Sora Ohashi, Junya Takayama, Tomoyuki Kajiwara, Yuki Arase
Few-shot text classification aims to classify inputs whose label has only a few examples.
no code implementations • Findings of the Association for Computational Linguistics 2020 • Junya Takayama, Yuki Arase
To control the specificity of generated responses, we add the distant supervision based on the co-occurrence degree and a PMI-based word prediction mechanism to a sequence-to-sequence model.
no code implementations • ACL 2020 • Sora Ohashi, Junya Takayama, Tomoyuki Kajiwara, Chenhui Chu, Yuki Arase
Advanced pre-trained models for text representation have achieved state-of-the-art performance on various text classification tasks.
1 code implementation • WS 2019 • Kozo Chikai, Junya Takayama, Yuki Arase
Specifically, our model generates domain-aware and sentiment-rich responses.
no code implementations • WS 2019 • Junya Takayama, Yuki Arase
A sequence-to-sequence model tends to generate generic responses with little information for input utterances.
no code implementations • ACL 2019 • Koji Tanaka, Junya Takayama, Yuki Arase
One significant drawback of such a neural network based approach is that the response generation process is a black-box, and how a specific response is generated is unclear.