Translations as additional contexts for sentence classification

Reinald Kim Amplayo, Kyungjae Lee, Jinyeong Yeo, Seung Won Hwang

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

Abstract

In sentence classification tasks, additional contexts, such as the neighboring sentences, may improve the accuracy of the classifier. However, such contexts are domain-dependent and thus cannot be used for another classification task with an inappropriate domain. In contrast, we propose the use of translated sentences as domain-free context that is always available regardless of the domain. We find that naive feature expansion of translations gains only marginal improvements and may decrease the performance of the classifier, due to possible inaccurate translations thus producing noisy sentence vectors. To this end, we present multiple context fixing attachment (MCFA), a series of modules attached to multiple sentence vectors to fix the noise in the vectors using the other sentence vectors as context. We show that our method performs competitively compared to previous models, achieving best classification performance on multiple data sets. We are the first to use translations as domainfree contexts for sentence classification.

Original languageEnglish
Title of host publicationProceedings of the 27th International Joint Conference on Artificial Intelligence, IJCAI 2018
EditorsJerome Lang
PublisherInternational Joint Conferences on Artificial Intelligence
Pages3955-3961
Number of pages7
ISBN (Electronic)9780999241127
Publication statusPublished - 2018 Jan 1
Event27th International Joint Conference on Artificial Intelligence, IJCAI 2018 - Stockholm, Sweden
Duration: 2018 Jul 132018 Jul 19

Publication series

NameIJCAI International Joint Conference on Artificial Intelligence
Volume2018-July
ISSN (Print)1045-0823

Other

Other27th International Joint Conference on Artificial Intelligence, IJCAI 2018
CountrySweden
CityStockholm
Period18/7/1318/7/19

Fingerprint

Classifiers

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence

Cite this

Amplayo, R. K., Lee, K., Yeo, J., & Hwang, S. W. (2018). Translations as additional contexts for sentence classification. In J. Lang (Ed.), Proceedings of the 27th International Joint Conference on Artificial Intelligence, IJCAI 2018 (pp. 3955-3961). (IJCAI International Joint Conference on Artificial Intelligence; Vol. 2018-July). International Joint Conferences on Artificial Intelligence.
Amplayo, Reinald Kim ; Lee, Kyungjae ; Yeo, Jinyeong ; Hwang, Seung Won. / Translations as additional contexts for sentence classification. Proceedings of the 27th International Joint Conference on Artificial Intelligence, IJCAI 2018. editor / Jerome Lang. International Joint Conferences on Artificial Intelligence, 2018. pp. 3955-3961 (IJCAI International Joint Conference on Artificial Intelligence).
@inproceedings{33b9ae2e0b1a4de8b0d661119f81c3ba,
title = "Translations as additional contexts for sentence classification",
abstract = "In sentence classification tasks, additional contexts, such as the neighboring sentences, may improve the accuracy of the classifier. However, such contexts are domain-dependent and thus cannot be used for another classification task with an inappropriate domain. In contrast, we propose the use of translated sentences as domain-free context that is always available regardless of the domain. We find that naive feature expansion of translations gains only marginal improvements and may decrease the performance of the classifier, due to possible inaccurate translations thus producing noisy sentence vectors. To this end, we present multiple context fixing attachment (MCFA), a series of modules attached to multiple sentence vectors to fix the noise in the vectors using the other sentence vectors as context. We show that our method performs competitively compared to previous models, achieving best classification performance on multiple data sets. We are the first to use translations as domainfree contexts for sentence classification.",
author = "Amplayo, {Reinald Kim} and Kyungjae Lee and Jinyeong Yeo and Hwang, {Seung Won}",
year = "2018",
month = "1",
day = "1",
language = "English",
series = "IJCAI International Joint Conference on Artificial Intelligence",
publisher = "International Joint Conferences on Artificial Intelligence",
pages = "3955--3961",
editor = "Jerome Lang",
booktitle = "Proceedings of the 27th International Joint Conference on Artificial Intelligence, IJCAI 2018",

}

Amplayo, RK, Lee, K, Yeo, J & Hwang, SW 2018, Translations as additional contexts for sentence classification. in J Lang (ed.), Proceedings of the 27th International Joint Conference on Artificial Intelligence, IJCAI 2018. IJCAI International Joint Conference on Artificial Intelligence, vol. 2018-July, International Joint Conferences on Artificial Intelligence, pp. 3955-3961, 27th International Joint Conference on Artificial Intelligence, IJCAI 2018, Stockholm, Sweden, 18/7/13.

Translations as additional contexts for sentence classification. / Amplayo, Reinald Kim; Lee, Kyungjae; Yeo, Jinyeong; Hwang, Seung Won.

Proceedings of the 27th International Joint Conference on Artificial Intelligence, IJCAI 2018. ed. / Jerome Lang. International Joint Conferences on Artificial Intelligence, 2018. p. 3955-3961 (IJCAI International Joint Conference on Artificial Intelligence; Vol. 2018-July).

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

TY - GEN

T1 - Translations as additional contexts for sentence classification

AU - Amplayo, Reinald Kim

AU - Lee, Kyungjae

AU - Yeo, Jinyeong

AU - Hwang, Seung Won

PY - 2018/1/1

Y1 - 2018/1/1

N2 - In sentence classification tasks, additional contexts, such as the neighboring sentences, may improve the accuracy of the classifier. However, such contexts are domain-dependent and thus cannot be used for another classification task with an inappropriate domain. In contrast, we propose the use of translated sentences as domain-free context that is always available regardless of the domain. We find that naive feature expansion of translations gains only marginal improvements and may decrease the performance of the classifier, due to possible inaccurate translations thus producing noisy sentence vectors. To this end, we present multiple context fixing attachment (MCFA), a series of modules attached to multiple sentence vectors to fix the noise in the vectors using the other sentence vectors as context. We show that our method performs competitively compared to previous models, achieving best classification performance on multiple data sets. We are the first to use translations as domainfree contexts for sentence classification.

AB - In sentence classification tasks, additional contexts, such as the neighboring sentences, may improve the accuracy of the classifier. However, such contexts are domain-dependent and thus cannot be used for another classification task with an inappropriate domain. In contrast, we propose the use of translated sentences as domain-free context that is always available regardless of the domain. We find that naive feature expansion of translations gains only marginal improvements and may decrease the performance of the classifier, due to possible inaccurate translations thus producing noisy sentence vectors. To this end, we present multiple context fixing attachment (MCFA), a series of modules attached to multiple sentence vectors to fix the noise in the vectors using the other sentence vectors as context. We show that our method performs competitively compared to previous models, achieving best classification performance on multiple data sets. We are the first to use translations as domainfree contexts for sentence classification.

UR - http://www.scopus.com/inward/record.url?scp=85055705637&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85055705637&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85055705637

T3 - IJCAI International Joint Conference on Artificial Intelligence

SP - 3955

EP - 3961

BT - Proceedings of the 27th International Joint Conference on Artificial Intelligence, IJCAI 2018

A2 - Lang, Jerome

PB - International Joint Conferences on Artificial Intelligence

ER -

Amplayo RK, Lee K, Yeo J, Hwang SW. Translations as additional contexts for sentence classification. In Lang J, editor, Proceedings of the 27th International Joint Conference on Artificial Intelligence, IJCAI 2018. International Joint Conferences on Artificial Intelligence. 2018. p. 3955-3961. (IJCAI International Joint Conference on Artificial Intelligence).