TY - GEN
T1 - Personalized Extractive Summarization Using an Ising Machine Towards Real-time Generation of Efficient and Coherent Dialogue Scenarios
AU - Takatsu, Hiroaki
AU - Kashikawa, Takahiro
AU - Kimura, Koichi
AU - Ando, Ryota
AU - Matsuyama, Yoichi
N1 - Funding Information:
This work was supported by Japan Science and Technology Agency (JST) Program for Creating STart-ups from Advanced Research and Technology (START), Grant Number JPMJST1912 “Commercialization of Socially-Intelligent Conversational AI Media Service.”
Publisher Copyright:
© 2021 Association for Computational Linguistics.
PY - 2021
Y1 - 2021
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85137996024&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85137996024&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85137996024
T3 - NLP for Conversational AI, NLP4ConvAI 2021 - Proceedings of the 3rd Workshop
SP - 16
EP - 29
BT - NLP for Conversational AI, NLP4ConvAI 2021 - Proceedings of the 3rd Workshop
A2 - Papangelis, Alexandros
A2 - Budzianowski, Pawel
A2 - Liu, Bing
A2 - Nouri, Elnaz
A2 - Rastogi, Abhinav
A2 - Chen, Yun-Nung
PB - Association for Computational Linguistics (ACL)
T2 - 3rd Workshop on Natural Language Processing for Conversational AI, NLP4ConvAI 2021
Y2 - 10 November 2021
ER -