Multi-level compare-aggregate model for text matching

Chunlin Xu; Zhiwei Lin; Hui Wang; Shengli Wu

doi:10.1109/IJCNN.2019.8852062

Multi-level compare-aggregate model for text matching

Chunlin Xu
, Zhiwei Lin
, Hui Wang
, Shengli Wu

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

3 Citations (Scopus)

Abstract

Text matching is important for a variety of natural language processing tasks, such as paraphrase identification and natural language inference. Recent studies have achieved very promising results under the compare-aggregate framework. A limitation of previous approaches following this framework is that they solely conduct matching at word level. In this paper, we propose a multi-level compare-aggregate model (MLCA), which matches each word in one text against the other text at three different levels, word level (word-by-word matching), phrase level (word-by-phrase matching) and sentence level (word-bysentence matching). Then the results of these levels of matching are aggregated for making final matching decision. We evaluate our model on two different tasks: paraphrase identification and natural language inference. Experimental results show that our model achieves the state-of-the-art performance on both tasks.

Original language	English
Title of host publication	2019 International Joint Conference on Neural Networks, IJCNN 2019: proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781728119854
ISBN (Print)	9781728119861
DOIs	https://doi.org/10.1109/IJCNN.2019.8852062
Publication status	Published - 30 Sept 2019
Externally published	Yes
Event	2019 International Joint Conference on Neural Networks, IJCNN 2019 - Budapest, Hungary Duration: 14 Jul 2019 → 19 Jul 2019

Publication series

Name	Proceedings of the International Joint Conference on Neural Networks
Volume	2019-July
ISSN (Print)	2161-4393
ISSN (Electronic)	2161-4407

Conference

Conference	2019 International Joint Conference on Neural Networks, IJCNN 2019
Country/Territory	Hungary
City	Budapest
Period	14/07/2019 → 19/07/2019

Bibliographical note

Funding Information:
ACKNOWLEDGMENT This work is partially funded by the VCRS scholarship, the EU Horizon 2020 Research and Innovation Programme under Grant 690238 for DESIREE Project, by the UK EPSRC under Grant EP/P031668/1, by the BT Ireland Innovation Centre (BTIIC).

Publisher Copyright:
© 2019 IEEE.

ASJC Scopus subject areas

Software
Artificial Intelligence

Access to Document

10.1109/IJCNN.2019.8852062Licence: Unspecified

Cite this

Xu, C., Lin, Z., Wang, H., & Wu, S. (2019). Multi-level compare-aggregate model for text matching. In 2019 International Joint Conference on Neural Networks, IJCNN 2019: proceedings Article 8852062 (Proceedings of the International Joint Conference on Neural Networks; Vol. 2019-July). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IJCNN.2019.8852062

@inproceedings{5fc6b78739f14f7dabc5233cb8818f27,

title = "Multi-level compare-aggregate model for text matching",

abstract = "Text matching is important for a variety of natural language processing tasks, such as paraphrase identification and natural language inference. Recent studies have achieved very promising results under the compare-aggregate framework. A limitation of previous approaches following this framework is that they solely conduct matching at word level. In this paper, we propose a multi-level compare-aggregate model (MLCA), which matches each word in one text against the other text at three different levels, word level (word-by-word matching), phrase level (word-by-phrase matching) and sentence level (word-bysentence matching). Then the results of these levels of matching are aggregated for making final matching decision. We evaluate our model on two different tasks: paraphrase identification and natural language inference. Experimental results show that our model achieves the state-of-the-art performance on both tasks.",

author = "Chunlin Xu and Zhiwei Lin and Hui Wang and Shengli Wu",

note = "Funding Information: ACKNOWLEDGMENT This work is partially funded by the VCRS scholarship, the EU Horizon 2020 Research and Innovation Programme under Grant 690238 for DESIREE Project, by the UK EPSRC under Grant EP/P031668/1, by the BT Ireland Innovation Centre (BTIIC). Publisher Copyright: {\textcopyright} 2019 IEEE.; 2019 International Joint Conference on Neural Networks, IJCNN 2019 ; Conference date: 14-07-2019 Through 19-07-2019",

year = "2019",

month = sep,

day = "30",

doi = "10.1109/IJCNN.2019.8852062",

language = "English",

isbn = "9781728119861",

series = "Proceedings of the International Joint Conference on Neural Networks",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2019 International Joint Conference on Neural Networks, IJCNN 2019: proceedings",

address = "United States",

}

Xu, C, Lin, Z , Wang, H & Wu, S 2019, Multi-level compare-aggregate model for text matching. in 2019 International Joint Conference on Neural Networks, IJCNN 2019: proceedings., 8852062, Proceedings of the International Joint Conference on Neural Networks, vol. 2019-July, Institute of Electrical and Electronics Engineers Inc., 2019 International Joint Conference on Neural Networks, IJCNN 2019, Budapest, Hungary, 14/07/2019. https://doi.org/10.1109/IJCNN.2019.8852062

Multi-level compare-aggregate model for text matching. / Xu, Chunlin; Lin, Zhiwei ; Wang, Hui et al.
2019 International Joint Conference on Neural Networks, IJCNN 2019: proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. 8852062 (Proceedings of the International Joint Conference on Neural Networks; Vol. 2019-July).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Multi-level compare-aggregate model for text matching

AU - Xu, Chunlin

AU - Lin, Zhiwei

AU - Wang, Hui

AU - Wu, Shengli

N1 - Funding Information: ACKNOWLEDGMENT This work is partially funded by the VCRS scholarship, the EU Horizon 2020 Research and Innovation Programme under Grant 690238 for DESIREE Project, by the UK EPSRC under Grant EP/P031668/1, by the BT Ireland Innovation Centre (BTIIC). Publisher Copyright: © 2019 IEEE.

PY - 2019/9/30

Y1 - 2019/9/30

N2 - Text matching is important for a variety of natural language processing tasks, such as paraphrase identification and natural language inference. Recent studies have achieved very promising results under the compare-aggregate framework. A limitation of previous approaches following this framework is that they solely conduct matching at word level. In this paper, we propose a multi-level compare-aggregate model (MLCA), which matches each word in one text against the other text at three different levels, word level (word-by-word matching), phrase level (word-by-phrase matching) and sentence level (word-bysentence matching). Then the results of these levels of matching are aggregated for making final matching decision. We evaluate our model on two different tasks: paraphrase identification and natural language inference. Experimental results show that our model achieves the state-of-the-art performance on both tasks.

AB - Text matching is important for a variety of natural language processing tasks, such as paraphrase identification and natural language inference. Recent studies have achieved very promising results under the compare-aggregate framework. A limitation of previous approaches following this framework is that they solely conduct matching at word level. In this paper, we propose a multi-level compare-aggregate model (MLCA), which matches each word in one text against the other text at three different levels, word level (word-by-word matching), phrase level (word-by-phrase matching) and sentence level (word-bysentence matching). Then the results of these levels of matching are aggregated for making final matching decision. We evaluate our model on two different tasks: paraphrase identification and natural language inference. Experimental results show that our model achieves the state-of-the-art performance on both tasks.

U2 - 10.1109/IJCNN.2019.8852062

DO - 10.1109/IJCNN.2019.8852062

M3 - Conference contribution

AN - SCOPUS:85073258559

SN - 9781728119861

T3 - Proceedings of the International Joint Conference on Neural Networks

BT - 2019 International Joint Conference on Neural Networks, IJCNN 2019: proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2019 International Joint Conference on Neural Networks, IJCNN 2019

Y2 - 14 July 2019 through 19 July 2019

ER -

Multi-level compare-aggregate model for text matching

Abstract

Publication series

Conference

Bibliographical note

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this