Personalized Extractive Summarization Using an Ising Machine Towards Real-time Generation of Efficient and Coherent Dialogue Scenarios

Hiroaki Takatsu, Takahiro Kashikawa, Koichi Kimura, Ryota Ando, Yoichi Matsuyama

研究成果: Conference contribution

抄録

We propose a personalized dialogue scenario generation system which transmits efficient and coherent information with a real-time extractive summarization method optimized by an Ising machine. The summarization problem is formulated as a quadratic unconstraint binary optimization (QUBO) problem, which extracts sentences that maximize the sum of the degree of user’s interest in the sentences of documents with the discourse structure of each document and the total utterance time as constraints. To evaluate the proposed method, we constructed a news article corpus with annotations of the discourse structure, users’ profiles, and interests in sentences and topics. The experimental results confirmed that a Digital Annealer, which is a simulated annealing-based Ising machine, can solve our QUBO model in a practical time without violating the constraints using this dataset.

本文言語English
ホスト出版物のタイトルNLP for Conversational AI, NLP4ConvAI 2021 - Proceedings of the 3rd Workshop
編集者Alexandros Papangelis, Pawel Budzianowski, Bing Liu, Elnaz Nouri, Abhinav Rastogi, Yun-Nung Chen
出版社Association for Computational Linguistics (ACL)
ページ16-29
ページ数14
ISBN(電子版)9781954085862
出版ステータスPublished - 2021
イベント3rd Workshop on Natural Language Processing for Conversational AI, NLP4ConvAI 2021 - Virtual, Online
継続期間: 2021 11月 10 → …

出版物シリーズ

名前NLP for Conversational AI, NLP4ConvAI 2021 - Proceedings of the 3rd Workshop

Conference

Conference3rd Workshop on Natural Language Processing for Conversational AI, NLP4ConvAI 2021
CityVirtual, Online
Period21/11/10 → …

ASJC Scopus subject areas

  • ソフトウェア
  • 言語および言語学
  • 言語学および言語
  • 人工知能

フィンガープリント

「Personalized Extractive Summarization Using an Ising Machine Towards Real-time Generation of Efficient and Coherent Dialogue Scenarios」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル