Discourse Chunking and its Application to Sentence Compression

C.E. Sporleder; M. Lapata

Discourse Chunking and its Application to Sentence Compression

C.E. Sporleder, M. Lapata

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

Abstract

In this paper we consider the problem of analysing sentence-level discourse structure. We introduce discourse chunking (i.e., the identification of intra-sentential nucleus and satellite spans) as an alternative to full-scale discourse parsing. Our experiments show that the proposed modelling approach yields results comparable to state-of-the-art while exploiting knowledge-lean features and small amounts of discourse annotations. We also demonstrate how discourse chunking can be successfully applied to a sentence compression task.

Original language	English
Title of host publication	Proceedings of the 2005 Human Language Technology Conference and the Conference on Empirical Methods in Natural Language Processing (HLT/EMNLP-05)
Place of Publication	Vancouver, Canada
Publisher	Unknown Publisher
Pages	8
Number of pages	8
Publication status	Published - 2005

Cite this

@inproceedings{8937f17f69b14fd488b3b7a8564ec2e0,

title = "Discourse Chunking and its Application to Sentence Compression",

abstract = "In this paper we consider the problem of analysing sentence-level discourse structure. We introduce discourse chunking (i.e., the identification of intra-sentential nucleus and satellite spans) as an alternative to full-scale discourse parsing. Our experiments show that the proposed modelling approach yields results comparable to state-of-the-art while exploiting knowledge-lean features and small amounts of discourse annotations. We also demonstrate how discourse chunking can be successfully applied to a sentence compression task.",

author = "C.E. Sporleder and M. Lapata",

note = "Pagination: 8",

year = "2005",

language = "English",

pages = "8",

booktitle = "Proceedings of the 2005 Human Language Technology Conference and the Conference on Empirical Methods in Natural Language Processing (HLT/EMNLP-05)",

publisher = "Unknown Publisher",

}

Discourse Chunking and its Application to Sentence Compression. / Sporleder, C.E.; Lapata, M.
Proceedings of the 2005 Human Language Technology Conference and the Conference on Empirical Methods in Natural Language Processing (HLT/EMNLP-05). Vancouver, Canada: Unknown Publisher, 2005. p. 8.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Discourse Chunking and its Application to Sentence Compression

AU - Sporleder, C.E.

AU - Lapata, M.

N1 - Pagination: 8

PY - 2005

Y1 - 2005

N2 - In this paper we consider the problem of analysing sentence-level discourse structure. We introduce discourse chunking (i.e., the identification of intra-sentential nucleus and satellite spans) as an alternative to full-scale discourse parsing. Our experiments show that the proposed modelling approach yields results comparable to state-of-the-art while exploiting knowledge-lean features and small amounts of discourse annotations. We also demonstrate how discourse chunking can be successfully applied to a sentence compression task.

AB - In this paper we consider the problem of analysing sentence-level discourse structure. We introduce discourse chunking (i.e., the identification of intra-sentential nucleus and satellite spans) as an alternative to full-scale discourse parsing. Our experiments show that the proposed modelling approach yields results comparable to state-of-the-art while exploiting knowledge-lean features and small amounts of discourse annotations. We also demonstrate how discourse chunking can be successfully applied to a sentence compression task.

M3 - Conference contribution

SP - 8

BT - Proceedings of the 2005 Human Language Technology Conference and the Conference on Empirical Methods in Natural Language Processing (HLT/EMNLP-05)

PB - Unknown Publisher

CY - Vancouver, Canada

ER -

Discourse Chunking and its Application to Sentence Compression

Abstract

Fingerprint

Cite this