Presentation 2018-07-07
Estimating Trivia Score for Trivia Sentence Extraction
Kazuya Niina, Kazutaka Shimada,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Dialogue systems have been increasingly important these days. In particular, non-task-oriented dialogue systems have been studied because of the success of neural network approaches such as seq2seq models. However, these models tend to generate simple responses such as "yes" and "ok." To construct a dialogue system that holds user's attention continuously, we need to generate utterances that capture the interest of the user. In this paper, we propose a method to extract trivia sentences for the purpose. Trivia information perhaps adds a surprise to users. Therefore, capturing trivia information is beneficial for dialogue systems. We estimate a trivia score of a sentence by using machine learning approaches. We obtained 0.81 on the $nDCG@10$ score by a ranking method.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Trivia / Estimating Trivia Score / Machine Learning / Learn to Rank
Paper # NLC2018-7
Date of Issue 2018-06-29 (NLC)

Conference Information
Committee NLC / IPSJ-ICS
Conference Date 2018/7/6(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Hokkaido University
Topics (in Japanese) (See Japanese page)
Topics (in English) Application of natural language processing and intelligent systems, and general topic of NLP
Chair Takeshi Sakaki(Hottolink)
Vice Chair Mitsuo Yoshida(Toyohashi Univ. of Tech.) / Kazutaka Shimada(Kyushu Inst. of Tech.)
Secretary Mitsuo Yoshida(Ryukoku Univ.) / Kazutaka Shimada(NTT)
Assistant Takeshi Kobayakawa(NHK) / Hiroki Sakaji(Univ. of Tokyo)

Paper Information
Registration To Technical Committee on Natural Language Understanding and Models of Communication / Special Interest Group on Intelligence and Complex Systems
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Estimating Trivia Score for Trivia Sentence Extraction
Sub Title (in English)
Keyword(1) Trivia
Keyword(2) Estimating Trivia Score
Keyword(3) Machine Learning
Keyword(4) Learn to Rank
1st Author's Name Kazuya Niina
1st Author's Affiliation Kyushu Institute of Technology(KIT)
2nd Author's Name Kazutaka Shimada
2nd Author's Affiliation Kyushu Institute of Technology(KIT)
Date 2018-07-07
Paper # NLC2018-7
Volume (vol) vol.118
Number (no) NLC-122
Page pp.pp.69-74(NLC),
#Pages 6
Date of Issue 2018-06-29 (NLC)