no code implementations • LREC 2022 • Yuji Naraki, Tetsuya Sakai, Yoshihiko Hayashi
Automatic dialogue summarization is a task used to succinctly summarize a dialogue transcript while correctly linking the speakers and their speech, which distinguishes this task from a conventional document summarization.
no code implementations • LREC 2022 • Yoshihiko Hayashi
A commonsense knowledge resource organizes common sense that is not necessarily correct all the time, but most people are expected to know or believe.
no code implementations • COLING 2022 • Masato Takatsuka, Tetsunori Kobayashi, Yoshihiko Hayashi
Although the fluency of automatically generated abstractive summaries has improved significantly with advanced methods, the inconsistency that remains in summarization is recognized as an issue to be addressed.
no code implementations • 8 Mar 2022 • Minori Toyoda, Kanata Suzuki, Yoshihiko Hayashi, Tetsuya OGATA
We experimentally evaluated our method using a paired dataset consisting of motion-captured actions and descriptions.
no code implementations • 17 Apr 2021 • Minori Toyoda, Kanata Suzuki, Hiroki Mori, Yoshihiko Hayashi, Tetsuya OGATA
These embeddings allow the robot to properly generate actions from unseen words that are not paired with actions in a dataset.
no code implementations • COLING 2020 • Hikari Tanabe, Tetsuji Ogawa, Tetsunori Kobayashi, Yoshihiko Hayashi
Recognition of the mental state of a human character in text is a major challenge in natural language processing.
no code implementations • LREC 2020 • Mika Hasegawa, Tetsunori Kobayashi, Yoshihiko Hayashi
Human semantic knowledge about concepts acquired through perceptual inputs and daily experiences can be expressed as a bundle of attributes.
no code implementations • WS 2019 • Mao Nakanishi, Tetsunori Kobayashi, Yoshihiko Hayashi
Conversational question generation is a novel area of NLP research which has a range of potential applications.
no code implementations • COLING 2018 • Mao Nakanishi, Tetsunori Kobayashi, Yoshihiko Hayashi
However, to realize human-like language comprehension ability, a machine should also be able to distinguish not-answerable questions (NAQs) from answerable questions.
no code implementations • WS 2017 • Kentaro Kanada, Tetsunori Kobayashi, Yoshihiko Hayashi
This paper proposes a method for classifying the type of lexical-semantic relation between a given pair of words.
no code implementations • COLING 2016 • Yoshihiko Hayashi
Evocation is a directed yet weighted semantic relationship between lexicalized concepts.
no code implementations • LREC 2016 • Yoshihiko Hayashi, Wentao Luo
This paper describes our independent effort for extending the monolingual semantic textual similarity (STS) task setting to multiple cross-lingual settings involving English, Japanese, and Chinese.
no code implementations • LREC 2016 • Yoshihiko Hayashi
Given lexical-semantic resources in different languages, it is useful to establish cross-lingual correspondences, preferably with semantic relation labels, between the concept nodes in these resources.
no code implementations • LREC 2014 • Yoshihiko Hayashi
The recent research direction toward multimodal semantic representation would be further advanced, if we could have a machinery to collect adequate images from the Web, given a target concept.
no code implementations • LREC 2012 • Yoshihiko Hayashi, Chiharu Narawa
iIt is often argued that a set of standard linguistic processing functionalities should be identified, with each of them given a formal specification.