2 code implementations • LREC 2022 • Kentaro Kurihara, Daisuke Kawahara, Tomohide Shibata
We build a Japanese NLU benchmark, JGLUE, from scratch without translation to measure the general NLU ability in Japanese.
no code implementations • EMNLP 2020 • Kazumasa Omura, Daisuke Kawahara, Sadao Kurohashi
We present a scalable, low-bias, and low-cost method for building a commonsense inference dataset that combines automatic extraction from a corpus and crowdsourcing.
no code implementations • 22 Feb 2024 • Ziqi Yin, Hao Wang, Kaito Horio, Daisuke Kawahara, Satoshi Sekine
We investigate the impact of politeness levels in prompts on the performance of large language models (LLMs).
no code implementations • 18 Jan 2024 • Hao Wang, Shuhei Kurita, Shuichiro Shimizu, Daisuke Kawahara
Audio-visual speech recognition (AVSR) is a multimodal extension of automatic speech recognition (ASR), using video as a complement to audio.
Audio-Visual Speech Recognition Automatic Speech Recognition +4
no code implementations • 17 Oct 2023 • Tomohito Kasahara, Daisuke Kawahara
Automatic evaluation of text generation is essential for improving the accuracy of generation tasks.
1 code implementation • 11 Oct 2023 • Tatsuya Ide, Eiki Murata, Daisuke Kawahara, Takato Yamazaki, Shengzhe Li, Kenta Shinzato, Toshinori Sato
In this paper, we propose PHALM, a method of building a knowledge graph from scratch, by prompting both crowdworkers and a large language model (LLM).
1 code implementation • 22 May 2023 • Hao Wang, Hirofumi Shimizu, Daisuke Kawahara
To solve this problem, we construct the first Classical-Chinese-to-Kanbun dataset in the world.
no code implementations • NAACL (ACL) 2022 • Ritvik Choudhary, Daisuke Kawahara
Building open-domain dialogue systems capable of rich human-like conversational ability is one of the fundamental challenges in language generation.
no code implementations • NAACL (ACL) 2022 • Tomohito Kasahara, Daisuke Kawahara, Nguyen Tung, Shengzhe Li, Kenta Shinzato, Toshinori Sato
Dialogue systems without consistent responses are not fascinating.
no code implementations • NAACL (ACL) 2022 • Ryoma Sakaeda, Daisuke Kawahara
We aim to overcome the lack of diversity in responses of current dialogue systems and to develop a dialogue system that is engaging as a conversational partner.
1 code implementation • ACL 2022 • Tatsuya Ide, Daisuke Kawahara
We hope that the constructed corpus will facilitate the study on emotion recognition in a dialogue and emotion-aware dialogue response generation.
no code implementations • NAACL 2021 • Tatsuya Ide, Daisuke Kawahara
For a computer to naturally interact with a human, it needs to be human-like.
1 code implementation • COLING 2020 • Nobuhiro Ueda, Daisuke Kawahara, Sadao Kurohashi
The meaning of natural language text is supported by cohesion among various kinds of entities, including coreference relations, predicate-argument structures, and bridging anaphora relations.
1 code implementation • 4 Oct 2020 • Qianying Liu, Wenyu Guan, Sujian Li, Fei Cheng, Daisuke Kawahara, Sadao Kurohashi
Automatically solving math word problems is a critical task in the field of natural language processing.
1 code implementation • Findings of the Association for Computational Linguistics 2020 • Ranran Haoran Zhang, Qianying Liu, Aysa Xuemo Fan, Heng Ji, Daojian Zeng, Fei Cheng, Daisuke Kawahara, Sadao Kurohashi
We propose a novel Sequence-to-Unordered-Multi-Tree (Seq2UMTree) model to minimize the effects of exposure bias by limiting the decoding length to three within a triplet and removing the order among triplets.
no code implementations • EMNLP (NLP-COVID19) 2020 • Akiko Aizawa, Frederic Bergeron, Junjie Chen, Fei Cheng, Katsuhiko Hayashi, Kentaro Inui, Hiroyoshi Ito, Daisuke Kawahara, Masaru Kitsuregawa, Hirokazu Kiyomaru, Masaki Kobayashi, Takashi Kodama, Sadao Kurohashi, Qianying Liu, Masaki Matsubara, Yusuke Miyao, Atsuyuki Morishima, Yugo Murawaki, Kazumasa Omura, Haiyue Song, Eiichiro Sumita, Shinji Suzuki, Ribeka Tanaka, Yu Tanaka, Masashi Toyoda, Nobuhiro Ueda, Honai Ueoka, Masao Utiyama, Ying Zhong
The global pandemic of COVID-19 has made the public pay close attention to related news, covering various domains, such as sanitation, treatment, and effects on education.
no code implementations • ACL 2020 • Yu Tanaka, Yugo Murawaki, Daisuke Kawahara, Sadao Kurohashi
User generated texts contain many typos for which correction is necessary for NLP systems to work.
no code implementations • LREC 2020 • Ritsuko Iwai, Daisuke Kawahara, Takatsune Kumada, Sadao Kurohashi
In this study, we collect personality words, using word embeddings, and construct a personality dictionary with weights for Big Five traits.
no code implementations • LREC 2020 • Ritsuko Iwai, Daisuke Kawahara, Takatsune Kumada, Sadao Kurohashi
Using them, we automatically extracted collocations between personality descriptors and driving-related behavior from a driving behavior and subjectivity corpus (1, 803, 328 sentences after filtering) and obtained unique 5, 334 collocations.
no code implementations • IJCNLP 2019 • Qianying Liu, Wenyv Guan, Sujian Li, Daisuke Kawahara
To address this problem, we propose a tree-structured decoding method that generates the abstract syntax tree of the equation in a top-down manner.
no code implementations • WS 2019 • Norio Takahashi, Tomohide Shibata, Daisuke Kawahara, Sadao Kurohashi
To improve the accuracy of predicate-argument structure (PAS) analysis, large-scale training data and knowledge for PAS analysis are indispensable.
no code implementations • WS 2019 • Hirokazu Kiyomaru, Kazumasa Omura, Yugo Murawaki, Daisuke Kawahara, Sadao Kurohashi
Typical event sequences are an important class of commonsense knowledge.
no code implementations • NAACL 2019 • Arseny Tolmachev, Daisuke Kawahara, Sadao Kurohashi
Morphological analyzers are trained on data hand-annotated with segmentation boundaries and part of speech tags.
1 code implementation • EMNLP 2018 • Arseny Tolmachev, Daisuke Kawahara, Sadao Kurohashi
We present a three-part toolkit for developing morphological analyzers for languages without natural word boundaries.
1 code implementation • COLING 2018 • Naoki Otani, Hirokazu Kiyomaru, Daisuke Kawahara, Sadao Kurohashi
Considerable effort has been devoted to building commonsense knowledge bases.
no code implementations • ACL 2018 • Shuhei Kurita, Daisuke Kawahara, Sadao Kurohashi
Japanese predicate-argument structure (PAS) analysis involves zero anaphora resolution, which is notoriously difficult.
no code implementations • NAACL 2018 • Abhishek Kumar, Daisuke Kawahara, Sadao Kurohashi
We propose a novel two-layered attention network based on Bidirectional Long Short-Term Memory for sentiment analysis.
no code implementations • WS 2017 • Daisuke Kawahara, Yuta Hayashibe, Hajime Morita, Sadao Kurohashi
This paper presents a joint model for morphological and dependency analysis based on automatically acquired lexical knowledge.
no code implementations • ACL 2017 • Shuhei Kurita, Daisuke Kawahara, Sadao Kurohashi
We present neural network-based joint models for Chinese word segmentation, POS tagging and dependency parsing.
no code implementations • EACL 2017 • Gongye Jin, Daisuke Kawahara, Sadao Kurohashi
To compensate the deficiency of the surface case frames, we compile deep case frames from automatic semantic roles.
no code implementations • 12 Dec 2016 • Xun Wang, Katsuhito Sudoh, Masaaki Nagata, Tomohide Shibata, Daisuke Kawahara, Sadao Kurohashi
This paper introduces a novel neural network model for question answering, the \emph{entity-based memory network}.
no code implementations • WS 2016 • Chenhui Chu, Toshiaki Nakazawa, Daisuke Kawahara, Sadao Kurohashi
Treebanks are curial for natural language processing (NLP).
no code implementations • COLING 2016 • Mo Shen, Wingmui Li, HyunJeong Choe, Chenhui Chu, Daisuke Kawahara, Sadao Kurohashi
In this paper, we propose a new annotation approach to Chinese word segmentation, part-of-speech (POS) tagging and dependency labelling that aims to overcome the two major issues in traditional morphology-based annotation: Inconsistency and data sparsity.
no code implementations • WS 2016 • Naoki Otani, Daisuke Kawahara, Sadao Kurohashi, Nobuhiro Kaji, Manabu Sassano
Commonsense knowledge is essential for fully understanding language in many situations.
no code implementations • LREC 2014 • Gongye Jin, Daisuke Kawahara, Sadao Kurohashi
The identification of various types of relations is a necessary step to allow computers to understand natural language text.
no code implementations • LREC 2014 • Daisuke Kawahara, Martha Palmer
In order to overcome this problem, we create a single classifier to be applied to rare or unseen verbs in a new text.