SEGBOT

A generic neural text segmentation model with pointer network

Jing Li, Aixin Sun, Shafiq Rayhan Joty

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

4 Citations (Scopus)

Abstract

Text segmentation is a fundamental task in natural language processing that comes in two levels of granularity: (i) segmenting a document into a sequence of topical segments (topic segmentation), and (ii) segmenting a sentence into a sequence of elementary discourse units (EDU segmentation). Traditional solutions to the two tasks heavily rely on carefully designed features. The recently proposed neural models do not need manual feature engineering, but they either suffer from sparse boundary tags or they cannot well handle the issue of variable size output vocabulary. We propose a generic end-to-end segmentation model called Seg-Bot. SegBot uses a bidirectional recurrent neural network to encode input text sequence. The model then uses another recurrent neural network together with a pointer network to select text boundaries in the input sequence. In this way, SegBot does not require hand-crafted features. More importantly, our model inherently handles the issue of variable size output vocabulary and the issue of sparse boundary tags. In our experiments, SegBot outperforms state-of-the-art models on both topic and EDU segmentation tasks.

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
Pages4166-4172
Number of pages7
Volume2018-July
ISBN (Electronic)9780999241127
Publication statusPublished - 1 Jan 2018
Event27th International Joint Conference on Artificial Intelligence, IJCAI 2018 - Stockholm, Sweden
Duration: 13 Jul 201819 Jul 2018

Other

Other27th International Joint Conference on Artificial Intelligence, IJCAI 2018
CountrySweden
CityStockholm
Period13/7/1819/7/18

Fingerprint

Recurrent neural networks
Processing
Experiments

ASJC Scopus subject areas

  • Artificial Intelligence

Cite this

Li, J., Sun, A., & Rayhan Joty, S. (2018). SEGBOT: A generic neural text segmentation model with pointer network. In J. Lang (Ed.), Proceedings of the 27th International Joint Conference on Artificial Intelligence, IJCAI 2018 (Vol. 2018-July, pp. 4166-4172). International Joint Conferences on Artificial Intelligence.

SEGBOT : A generic neural text segmentation model with pointer network. / Li, Jing; Sun, Aixin; Rayhan Joty, Shafiq.

Proceedings of the 27th International Joint Conference on Artificial Intelligence, IJCAI 2018. ed. / Jerome Lang. Vol. 2018-July International Joint Conferences on Artificial Intelligence, 2018. p. 4166-4172.

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

Li, J, Sun, A & Rayhan Joty, S 2018, SEGBOT: A generic neural text segmentation model with pointer network. in J Lang (ed.), Proceedings of the 27th International Joint Conference on Artificial Intelligence, IJCAI 2018. vol. 2018-July, International Joint Conferences on Artificial Intelligence, pp. 4166-4172, 27th International Joint Conference on Artificial Intelligence, IJCAI 2018, Stockholm, Sweden, 13/7/18.
Li J, Sun A, Rayhan Joty S. SEGBOT: A generic neural text segmentation model with pointer network. In Lang J, editor, Proceedings of the 27th International Joint Conference on Artificial Intelligence, IJCAI 2018. Vol. 2018-July. International Joint Conferences on Artificial Intelligence. 2018. p. 4166-4172
Li, Jing ; Sun, Aixin ; Rayhan Joty, Shafiq. / SEGBOT : A generic neural text segmentation model with pointer network. Proceedings of the 27th International Joint Conference on Artificial Intelligence, IJCAI 2018. editor / Jerome Lang. Vol. 2018-July International Joint Conferences on Artificial Intelligence, 2018. pp. 4166-4172
@inproceedings{e0b6fc8c4c2a456c8a33911563993d68,
title = "SEGBOT: A generic neural text segmentation model with pointer network",
abstract = "Text segmentation is a fundamental task in natural language processing that comes in two levels of granularity: (i) segmenting a document into a sequence of topical segments (topic segmentation), and (ii) segmenting a sentence into a sequence of elementary discourse units (EDU segmentation). Traditional solutions to the two tasks heavily rely on carefully designed features. The recently proposed neural models do not need manual feature engineering, but they either suffer from sparse boundary tags or they cannot well handle the issue of variable size output vocabulary. We propose a generic end-to-end segmentation model called Seg-Bot. SegBot uses a bidirectional recurrent neural network to encode input text sequence. The model then uses another recurrent neural network together with a pointer network to select text boundaries in the input sequence. In this way, SegBot does not require hand-crafted features. More importantly, our model inherently handles the issue of variable size output vocabulary and the issue of sparse boundary tags. In our experiments, SegBot outperforms state-of-the-art models on both topic and EDU segmentation tasks.",
author = "Jing Li and Aixin Sun and {Rayhan Joty}, Shafiq",
year = "2018",
month = "1",
day = "1",
language = "English",
volume = "2018-July",
pages = "4166--4172",
editor = "Jerome Lang",
booktitle = "Proceedings of the 27th International Joint Conference on Artificial Intelligence, IJCAI 2018",
publisher = "International Joint Conferences on Artificial Intelligence",

}

TY - GEN

T1 - SEGBOT

T2 - A generic neural text segmentation model with pointer network

AU - Li, Jing

AU - Sun, Aixin

AU - Rayhan Joty, Shafiq

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Text segmentation is a fundamental task in natural language processing that comes in two levels of granularity: (i) segmenting a document into a sequence of topical segments (topic segmentation), and (ii) segmenting a sentence into a sequence of elementary discourse units (EDU segmentation). Traditional solutions to the two tasks heavily rely on carefully designed features. The recently proposed neural models do not need manual feature engineering, but they either suffer from sparse boundary tags or they cannot well handle the issue of variable size output vocabulary. We propose a generic end-to-end segmentation model called Seg-Bot. SegBot uses a bidirectional recurrent neural network to encode input text sequence. The model then uses another recurrent neural network together with a pointer network to select text boundaries in the input sequence. In this way, SegBot does not require hand-crafted features. More importantly, our model inherently handles the issue of variable size output vocabulary and the issue of sparse boundary tags. In our experiments, SegBot outperforms state-of-the-art models on both topic and EDU segmentation tasks.

AB - Text segmentation is a fundamental task in natural language processing that comes in two levels of granularity: (i) segmenting a document into a sequence of topical segments (topic segmentation), and (ii) segmenting a sentence into a sequence of elementary discourse units (EDU segmentation). Traditional solutions to the two tasks heavily rely on carefully designed features. The recently proposed neural models do not need manual feature engineering, but they either suffer from sparse boundary tags or they cannot well handle the issue of variable size output vocabulary. We propose a generic end-to-end segmentation model called Seg-Bot. SegBot uses a bidirectional recurrent neural network to encode input text sequence. The model then uses another recurrent neural network together with a pointer network to select text boundaries in the input sequence. In this way, SegBot does not require hand-crafted features. More importantly, our model inherently handles the issue of variable size output vocabulary and the issue of sparse boundary tags. In our experiments, SegBot outperforms state-of-the-art models on both topic and EDU segmentation tasks.

UR - http://www.scopus.com/inward/record.url?scp=85055673414&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85055673414&partnerID=8YFLogxK

M3 - Conference contribution

VL - 2018-July

SP - 4166

EP - 4172

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

A2 - Lang, Jerome

PB - International Joint Conferences on Artificial Intelligence

ER -