Machine-translated knowledge transfer for commonsense causal reasoning

Jinyoung Yeo, Geungyu Wang, Hyunsouk Cho, Seungtaek Choi, Seung Won Hwang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

This paper studies the problem of multilingual causal reasoning in resource-poor languages. Existing approaches, translating into the most probable resource-rich language such as English, suffer in the presence of translation and language gaps between different cultural area, which leads to the loss of causality. To overcome these challenges, our goal is thus to identify key techniques to construct a new causality network of cause-effect terms, targeted for the machine-translated English, but without any language-specific knowledge of resource-poor languages. In our evaluations with three languages, Korean, Chinese, and French, our proposed method consistently outperforms all baselines, achieving up-to 69.0% reasoning accuracy, which is close to the state-of-the-art accuracy 70.2% achieved on English.

Original languageEnglish
Title of host publication32nd AAAI Conference on Artificial Intelligence, AAAI 2018
PublisherAAAI press
Pages2021-2028
Number of pages8
ISBN (Electronic)9781577358008
Publication statusPublished - 2018 Jan 1
Event32nd AAAI Conference on Artificial Intelligence, AAAI 2018 - New Orleans, United States
Duration: 2018 Feb 22018 Feb 7

Publication series

Name32nd AAAI Conference on Artificial Intelligence, AAAI 2018

Other

Other32nd AAAI Conference on Artificial Intelligence, AAAI 2018
CountryUnited States
CityNew Orleans
Period18/2/218/2/7

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence

Cite this

Yeo, J., Wang, G., Cho, H., Choi, S., & Hwang, S. W. (2018). Machine-translated knowledge transfer for commonsense causal reasoning. In 32nd AAAI Conference on Artificial Intelligence, AAAI 2018 (pp. 2021-2028). (32nd AAAI Conference on Artificial Intelligence, AAAI 2018). AAAI press.
Yeo, Jinyoung ; Wang, Geungyu ; Cho, Hyunsouk ; Choi, Seungtaek ; Hwang, Seung Won. / Machine-translated knowledge transfer for commonsense causal reasoning. 32nd AAAI Conference on Artificial Intelligence, AAAI 2018. AAAI press, 2018. pp. 2021-2028 (32nd AAAI Conference on Artificial Intelligence, AAAI 2018).
@inproceedings{7d4bcb6b099243c982c61604f12911cc,
title = "Machine-translated knowledge transfer for commonsense causal reasoning",
abstract = "This paper studies the problem of multilingual causal reasoning in resource-poor languages. Existing approaches, translating into the most probable resource-rich language such as English, suffer in the presence of translation and language gaps between different cultural area, which leads to the loss of causality. To overcome these challenges, our goal is thus to identify key techniques to construct a new causality network of cause-effect terms, targeted for the machine-translated English, but without any language-specific knowledge of resource-poor languages. In our evaluations with three languages, Korean, Chinese, and French, our proposed method consistently outperforms all baselines, achieving up-to 69.0{\%} reasoning accuracy, which is close to the state-of-the-art accuracy 70.2{\%} achieved on English.",
author = "Jinyoung Yeo and Geungyu Wang and Hyunsouk Cho and Seungtaek Choi and Hwang, {Seung Won}",
year = "2018",
month = "1",
day = "1",
language = "English",
series = "32nd AAAI Conference on Artificial Intelligence, AAAI 2018",
publisher = "AAAI press",
pages = "2021--2028",
booktitle = "32nd AAAI Conference on Artificial Intelligence, AAAI 2018",

}

Yeo, J, Wang, G, Cho, H, Choi, S & Hwang, SW 2018, Machine-translated knowledge transfer for commonsense causal reasoning. in 32nd AAAI Conference on Artificial Intelligence, AAAI 2018. 32nd AAAI Conference on Artificial Intelligence, AAAI 2018, AAAI press, pp. 2021-2028, 32nd AAAI Conference on Artificial Intelligence, AAAI 2018, New Orleans, United States, 18/2/2.

Machine-translated knowledge transfer for commonsense causal reasoning. / Yeo, Jinyoung; Wang, Geungyu; Cho, Hyunsouk; Choi, Seungtaek; Hwang, Seung Won.

32nd AAAI Conference on Artificial Intelligence, AAAI 2018. AAAI press, 2018. p. 2021-2028 (32nd AAAI Conference on Artificial Intelligence, AAAI 2018).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Machine-translated knowledge transfer for commonsense causal reasoning

AU - Yeo, Jinyoung

AU - Wang, Geungyu

AU - Cho, Hyunsouk

AU - Choi, Seungtaek

AU - Hwang, Seung Won

PY - 2018/1/1

Y1 - 2018/1/1

N2 - This paper studies the problem of multilingual causal reasoning in resource-poor languages. Existing approaches, translating into the most probable resource-rich language such as English, suffer in the presence of translation and language gaps between different cultural area, which leads to the loss of causality. To overcome these challenges, our goal is thus to identify key techniques to construct a new causality network of cause-effect terms, targeted for the machine-translated English, but without any language-specific knowledge of resource-poor languages. In our evaluations with three languages, Korean, Chinese, and French, our proposed method consistently outperforms all baselines, achieving up-to 69.0% reasoning accuracy, which is close to the state-of-the-art accuracy 70.2% achieved on English.

AB - This paper studies the problem of multilingual causal reasoning in resource-poor languages. Existing approaches, translating into the most probable resource-rich language such as English, suffer in the presence of translation and language gaps between different cultural area, which leads to the loss of causality. To overcome these challenges, our goal is thus to identify key techniques to construct a new causality network of cause-effect terms, targeted for the machine-translated English, but without any language-specific knowledge of resource-poor languages. In our evaluations with three languages, Korean, Chinese, and French, our proposed method consistently outperforms all baselines, achieving up-to 69.0% reasoning accuracy, which is close to the state-of-the-art accuracy 70.2% achieved on English.

UR - http://www.scopus.com/inward/record.url?scp=85060442084&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85060442084&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85060442084

T3 - 32nd AAAI Conference on Artificial Intelligence, AAAI 2018

SP - 2021

EP - 2028

BT - 32nd AAAI Conference on Artificial Intelligence, AAAI 2018

PB - AAAI press

ER -

Yeo J, Wang G, Cho H, Choi S, Hwang SW. Machine-translated knowledge transfer for commonsense causal reasoning. In 32nd AAAI Conference on Artificial Intelligence, AAAI 2018. AAAI press. 2018. p. 2021-2028. (32nd AAAI Conference on Artificial Intelligence, AAAI 2018).