Presentation 2019-01-22
Logical Failure Detection in Question-and-Answer Sessions Towards A Practical Mock Interview System
Kohei Shimizu, Komei Arasawa, Ryohei Watanabe, Shun Hattori,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In job hunting, oral interviews are important examinations for job hunters to appeal to their targeted companies and for companies to acquire human resources who they want to seek. In oral interviews, interviewers of companies scrutinize each job hunter from various viewpoints. Among them, "logical thinking" is one of especially-important factors. In recent years, the questions to find out whether or not each job hunter can answer them with logical thinking are often asked in oral interviews. However, it is difficult for a job hunter to judge whether or not s/he was evaluated to be able to answer logically by her/his targeted companies, because there is no oppotunity for her/him to receive feedback about it in actual interviews. Meanwhile, it is difficult for a job hunter to improve her/his answers using the existing mock interview systems, because they cannot detect a logical failure in her/his answers. Therefore, this paper proposes a more practical mock interview system that aims at helping job hunters to improve their answers by themselves, and that automatically detects logical failures in a job hunter's answer to a company's question by estimating the relationship between sentences focusing on the important words and the part of speech (in particular, conjunction and adverbial particle) of words in her/his answer.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Mock Interview / Question and Answering / Machine Learning / Word2Vec / TF-IDF
Paper # IN2018-83
Date of Issue 2019-01-14 (IN)

Conference Information
Committee IN
Conference Date 2019/1/21(2days)
Place (in Japanese) (See Japanese page)
Place (in English) WINC AICHI
Topics (in Japanese) (See Japanese page)
Topics (in English) Contents Distribution, Social Networking Services, Data Analytics and Processing Platform, Big data, etc.
Chair Takuji Kishida(NTT-AT)
Vice Chair Kenji Ishida(Hiroshima City Univ.)
Secretary Kenji Ishida(KDDI Research)
Assistant

Paper Information
Registration To Technical Committee on Information Networks
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Logical Failure Detection in Question-and-Answer Sessions Towards A Practical Mock Interview System
Sub Title (in English)
Keyword(1) Mock Interview
Keyword(2) Question and Answering
Keyword(3) Machine Learning
Keyword(4) Word2Vec
Keyword(5) TF-IDF
1st Author's Name Kohei Shimizu
1st Author's Affiliation Muroran Institute of Technology(Muroran Inst. of Tech.)
2nd Author's Name Komei Arasawa
2nd Author's Affiliation Muroran Institute of Technology(Muroran Inst. of Tech.)
3rd Author's Name Ryohei Watanabe
3rd Author's Affiliation Muroran Institute of Technology(Muroran Inst. of Tech.)
4th Author's Name Shun Hattori
4th Author's Affiliation Muroran Institute of Technology(Muroran Inst. of Tech.)
Date 2019-01-22
Paper # IN2018-83
Volume (vol) vol.118
Number (no) IN-408
Page pp.pp.63-68(IN),
#Pages 6
Date of Issue 2019-01-14 (IN)