no code implementations • LREC 2022 • Tatsuya Ishigaki, Suzuko Nishino, Sohei Washino, Hiroki Igarashi, Yukari Nagai, Yuichi Washida, Akihiko Murai
The contributions are: 1) we propose document retrieval and comment generation tasks for horizon scanning, 2) create and analyze a new dataset, and 3) report the performance of several models and show that comment generation tasks are challenging.
no code implementations • INLG (ACL) 2021 • Tatsuya Ishigaki, Goran Topic, Yumi Hamazono, Hiroshi Noji, Ichiro Kobayashi, Yusuke Miyao, Hiroya Takamura
In this study, we introduce a new large-scale dataset that contains aligned video data, structured numerical data, and transcribed commentaries that consist of 129, 226 utterances in 1, 389 races in a game.
no code implementations • 12 Apr 2024 • Kosuke Takahashi, Takahiro Omi, Kosuke Arima, Tatsuya Ishigaki
This study explores the combination of a non-English language and a high-demand industry domain, focusing on a Japanese business-specific LLM.
1 code implementation • 3 Apr 2024 • Masayuki Kawarada, Tatsuya Ishigaki, Hiroya Takamura
Large language models (LLMs) have been applied to a wide range of data-to-text generation tasks, including tables, graphs, and time-series numerical data-to-text settings.
no code implementations • 12 Oct 2023 • Kosuke Takahashi, Takahiro Omi, Kosuke Arima, Tatsuya Ishigaki
This paper presents a simple and cost-effective method for synthesizing data to train question-answering systems.
1 code implementation • COLING 2020 • Yui Uehara, Tatsuya Ishigaki, Kasumi Aoki, Hiroshi Noji, Keiichi Goshima, Ichiro Kobayashi, Hiroya Takamura, Yusuke Miyao
Existing models for data-to-text tasks generate fluent but sometimes incorrect sentences e. g., {``}Nikkei gains{''} is generated when {``}Nikkei drops{''} is expected.
no code implementations • WS 2019 • Kasumi Aoki, Akira Miyazawa, Tatsuya Ishigaki, Tatsuya Aoki, Hiroshi Noji, Keiichi Goshima, Ichiro Kobayashi, Hiroya Takamura, Yusuke Miyao
We propose a data-to-document generator that can easily control the contents of output texts based on a neural language model.
no code implementations • RANLP 2019 • Tatsuya Ishigaki, Hidetaka Kamigaito, Hiroya Takamura, Manabu Okumura
To incorporate the information of a discourse tree structure into the neural network-based summarizers, we propose a discourse-aware neural extractive summarizer which can explicitly take into account the discourse dependency tree structure of the source document.
2 code implementations • ACL 2019 • Hayate Iso, Yui Uehara, Tatsuya Ishigaki, Hiroshi Noji, Eiji Aramaki, Ichiro Kobayashi, Yusuke Miyao, Naoaki Okazaki, Hiroya Takamura
We propose a data-to-text generation model with two modules, one for tracking and the other for text generation.
1 code implementation • WS 2018 • Tatsuya Aoki, Akira Miyazawa, Tatsuya Ishigaki, Keiichi Goshima, Kasumi Aoki, Ichiro Kobayashi, Hiroya Takamura, Yusuke Miyao
Comments on a stock market often include the reason or cause of changes in stock prices, such as {``}Nikkei turns lower as yen{'}s rise hits exporters.
no code implementations • IJCNLP 2017 • Tatsuya Ishigaki, Hiroya Takamura, Manabu Okumura
In this research, we propose the task of question summarization.