Automatic prediction of misconceptions in multilingual computer-mediated communication

Naomi Yamashita, Toru Ishida

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

20 Citations (Scopus)

Abstract

Multilingual communities using machine translation to overcome language barriers are showing up with increasing frequency. However, when a large number of translation errors get mixed into conversations, users have difficulty completely understanding each other. In this paper, we focus on misconceptions found in high volume in actual online conversations using machine translation. We first examine the response patterns in machine translation-mediated communication and associate them with misconceptions. Analysis results indicate that response messages to include misconceptions posted via machine translation tend to be incoherent, often focusing on short phrases of the original message. Next, based on the analysis results, we propose a method that automatically predicts the occurrence of misconceptions in each dialogue. The proposed method assesses the tendency of each dialogue including misconceptions by calculating the gaps between the regular discussion thread (syntactic thread) and the discussion thread based on lexical cohesion (semantic thread). Verification results show significant positive correlation between actual misconception frequency and gaps between syntactic and semantic threads, which indicate the validity of the method.

Original languageEnglish
Title of host publicationIUI 06 - 2006 International Conference on Intelligent User Interfaces
Pages62-69
Number of pages8
DOIs
Publication statusPublished - 2006 Jul 24
Externally publishedYes
EventIUI 06 - 2006 International Conference on Intelligent User Interfaces - Sydney, Australia
Duration: 2005 Jan 292005 Feb 1

Publication series

NameInternational Conference on Intelligent User Interfaces, Proceedings IUI
Volume2006

Conference

ConferenceIUI 06 - 2006 International Conference on Intelligent User Interfaces
CountryAustralia
CitySydney
Period05/1/2905/2/1

Fingerprint

Syntactics
Semantics
Communication

Keywords

  • Computer-Mediated Communication
  • Machine Translation
  • Misconception
  • Multilingual Groups

ASJC Scopus subject areas

  • Software
  • Human-Computer Interaction

Cite this

Yamashita, N., & Ishida, T. (2006). Automatic prediction of misconceptions in multilingual computer-mediated communication. In IUI 06 - 2006 International Conference on Intelligent User Interfaces (pp. 62-69). (International Conference on Intelligent User Interfaces, Proceedings IUI; Vol. 2006). https://doi.org/10.1145/1111449.1111469

Automatic prediction of misconceptions in multilingual computer-mediated communication. / Yamashita, Naomi; Ishida, Toru.

IUI 06 - 2006 International Conference on Intelligent User Interfaces. 2006. p. 62-69 (International Conference on Intelligent User Interfaces, Proceedings IUI; Vol. 2006).

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

Yamashita, N & Ishida, T 2006, Automatic prediction of misconceptions in multilingual computer-mediated communication. in IUI 06 - 2006 International Conference on Intelligent User Interfaces. International Conference on Intelligent User Interfaces, Proceedings IUI, vol. 2006, pp. 62-69, IUI 06 - 2006 International Conference on Intelligent User Interfaces, Sydney, Australia, 05/1/29. https://doi.org/10.1145/1111449.1111469
Yamashita N, Ishida T. Automatic prediction of misconceptions in multilingual computer-mediated communication. In IUI 06 - 2006 International Conference on Intelligent User Interfaces. 2006. p. 62-69. (International Conference on Intelligent User Interfaces, Proceedings IUI). https://doi.org/10.1145/1111449.1111469
Yamashita, Naomi ; Ishida, Toru. / Automatic prediction of misconceptions in multilingual computer-mediated communication. IUI 06 - 2006 International Conference on Intelligent User Interfaces. 2006. pp. 62-69 (International Conference on Intelligent User Interfaces, Proceedings IUI).
@inproceedings{76bc403207224f1f9ca0bb2318444a79,
title = "Automatic prediction of misconceptions in multilingual computer-mediated communication",
abstract = "Multilingual communities using machine translation to overcome language barriers are showing up with increasing frequency. However, when a large number of translation errors get mixed into conversations, users have difficulty completely understanding each other. In this paper, we focus on misconceptions found in high volume in actual online conversations using machine translation. We first examine the response patterns in machine translation-mediated communication and associate them with misconceptions. Analysis results indicate that response messages to include misconceptions posted via machine translation tend to be incoherent, often focusing on short phrases of the original message. Next, based on the analysis results, we propose a method that automatically predicts the occurrence of misconceptions in each dialogue. The proposed method assesses the tendency of each dialogue including misconceptions by calculating the gaps between the regular discussion thread (syntactic thread) and the discussion thread based on lexical cohesion (semantic thread). Verification results show significant positive correlation between actual misconception frequency and gaps between syntactic and semantic threads, which indicate the validity of the method.",
keywords = "Computer-Mediated Communication, Machine Translation, Misconception, Multilingual Groups",
author = "Naomi Yamashita and Toru Ishida",
year = "2006",
month = "7",
day = "24",
doi = "10.1145/1111449.1111469",
language = "English",
isbn = "1595932879",
series = "International Conference on Intelligent User Interfaces, Proceedings IUI",
pages = "62--69",
booktitle = "IUI 06 - 2006 International Conference on Intelligent User Interfaces",

}

TY - GEN

T1 - Automatic prediction of misconceptions in multilingual computer-mediated communication

AU - Yamashita, Naomi

AU - Ishida, Toru

PY - 2006/7/24

Y1 - 2006/7/24

N2 - Multilingual communities using machine translation to overcome language barriers are showing up with increasing frequency. However, when a large number of translation errors get mixed into conversations, users have difficulty completely understanding each other. In this paper, we focus on misconceptions found in high volume in actual online conversations using machine translation. We first examine the response patterns in machine translation-mediated communication and associate them with misconceptions. Analysis results indicate that response messages to include misconceptions posted via machine translation tend to be incoherent, often focusing on short phrases of the original message. Next, based on the analysis results, we propose a method that automatically predicts the occurrence of misconceptions in each dialogue. The proposed method assesses the tendency of each dialogue including misconceptions by calculating the gaps between the regular discussion thread (syntactic thread) and the discussion thread based on lexical cohesion (semantic thread). Verification results show significant positive correlation between actual misconception frequency and gaps between syntactic and semantic threads, which indicate the validity of the method.

AB - Multilingual communities using machine translation to overcome language barriers are showing up with increasing frequency. However, when a large number of translation errors get mixed into conversations, users have difficulty completely understanding each other. In this paper, we focus on misconceptions found in high volume in actual online conversations using machine translation. We first examine the response patterns in machine translation-mediated communication and associate them with misconceptions. Analysis results indicate that response messages to include misconceptions posted via machine translation tend to be incoherent, often focusing on short phrases of the original message. Next, based on the analysis results, we propose a method that automatically predicts the occurrence of misconceptions in each dialogue. The proposed method assesses the tendency of each dialogue including misconceptions by calculating the gaps between the regular discussion thread (syntactic thread) and the discussion thread based on lexical cohesion (semantic thread). Verification results show significant positive correlation between actual misconception frequency and gaps between syntactic and semantic threads, which indicate the validity of the method.

KW - Computer-Mediated Communication

KW - Machine Translation

KW - Misconception

KW - Multilingual Groups

UR - http://www.scopus.com/inward/record.url?scp=33746074110&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33746074110&partnerID=8YFLogxK

U2 - 10.1145/1111449.1111469

DO - 10.1145/1111449.1111469

M3 - Conference contribution

SN - 1595932879

SN - 9781595932877

T3 - International Conference on Intelligent User Interfaces, Proceedings IUI

SP - 62

EP - 69

BT - IUI 06 - 2006 International Conference on Intelligent User Interfaces

ER -