Learning to Summarise Related Sentences

Publikation: Beiträge in SammelwerkenAufsätze in KonferenzbändenForschungbegutachtet

Standard

Learning to Summarise Related Sentences. / Tzouridis, Emmanouil ; Nasir, Jamal Abdul; Brefeld, Ulf.
COLING 2014 - 25th International Conference on Computational Linguistics, Proceedings of COLING 2014: Technical Papers. Dublin: Association for Computational Linguistics (ACL), 2014. S. 1636-1647 (COLING 2014 - 25th International Conference on Computational Linguistics, Proceedings of COLING 2014: Technical Papers).

Publikation: Beiträge in SammelwerkenAufsätze in KonferenzbändenForschungbegutachtet

Harvard

Tzouridis, E, Nasir, JA & Brefeld, U 2014, Learning to Summarise Related Sentences. in COLING 2014 - 25th International Conference on Computational Linguistics, Proceedings of COLING 2014: Technical Papers. COLING 2014 - 25th International Conference on Computational Linguistics, Proceedings of COLING 2014: Technical Papers, Association for Computational Linguistics (ACL), Dublin, S. 1636-1647, 25th International Conference on Computational Linguistics - COLING 2014 , Dublin, Irland, 23.08.14. <https://www.aclweb.org/anthology/C14-1.pdf>

APA

Tzouridis, E., Nasir, J. A., & Brefeld, U. (2014). Learning to Summarise Related Sentences. In COLING 2014 - 25th International Conference on Computational Linguistics, Proceedings of COLING 2014: Technical Papers (S. 1636-1647). (COLING 2014 - 25th International Conference on Computational Linguistics, Proceedings of COLING 2014: Technical Papers). Association for Computational Linguistics (ACL). https://www.aclweb.org/anthology/C14-1.pdf

Vancouver

Tzouridis E, Nasir JA, Brefeld U. Learning to Summarise Related Sentences. in COLING 2014 - 25th International Conference on Computational Linguistics, Proceedings of COLING 2014: Technical Papers. Dublin: Association for Computational Linguistics (ACL). 2014. S. 1636-1647. (COLING 2014 - 25th International Conference on Computational Linguistics, Proceedings of COLING 2014: Technical Papers).

Bibtex

@inbook{fef3e9f68f0646628aa1d42b1beed360,
title = "Learning to Summarise Related Sentences",
abstract = "We cast multi-sentence compression as a structured prediction problem. Related sentences are represented by a word graph so that summaries constitute paths in the graph (Filippova, 2010). We devise a parameterised shortest path algorithm that can be written as a generalised linear model in a joint space of word graphs and compressions. We use a large-margin approach to adapt parameterised edge weights to the data such that the shortest path is identical to the desired summary. Decoding during training is performed in polynomial time using loss augmented inference. Empirically, we compare our approach to the state-of-the-art in graph-based multi-sentence compression and observe significant improvements of about 7% in ROUGE F-measure and 8% in BLEU score, respectively.",
keywords = "Informatics, Business informatics",
author = "Emmanouil Tzouridis and Nasir, {Jamal Abdul} and Ulf Brefeld",
year = "2014",
language = "English",
isbn = "978-1-941643-26-6",
series = "COLING 2014 - 25th International Conference on Computational Linguistics, Proceedings of COLING 2014: Technical Papers",
publisher = "Association for Computational Linguistics (ACL)",
pages = "1636--1647",
booktitle = "COLING 2014 - 25th International Conference on Computational Linguistics, Proceedings of COLING 2014",
address = "United States",
note = "25th International Conference on Computational Linguistics - COLING 2014 , COLING 2014 ; Conference date: 23-08-2014 Through 29-08-2014",
url = "https://aclanthology.info/volumes/proceedings-of-coling-2014-the-25th-international-conference-on-computational-linguistics-technical-papers",

}

RIS

TY - CHAP

T1 - Learning to Summarise Related Sentences

AU - Tzouridis, Emmanouil

AU - Nasir, Jamal Abdul

AU - Brefeld, Ulf

N1 - Conference code: 25

PY - 2014

Y1 - 2014

N2 - We cast multi-sentence compression as a structured prediction problem. Related sentences are represented by a word graph so that summaries constitute paths in the graph (Filippova, 2010). We devise a parameterised shortest path algorithm that can be written as a generalised linear model in a joint space of word graphs and compressions. We use a large-margin approach to adapt parameterised edge weights to the data such that the shortest path is identical to the desired summary. Decoding during training is performed in polynomial time using loss augmented inference. Empirically, we compare our approach to the state-of-the-art in graph-based multi-sentence compression and observe significant improvements of about 7% in ROUGE F-measure and 8% in BLEU score, respectively.

AB - We cast multi-sentence compression as a structured prediction problem. Related sentences are represented by a word graph so that summaries constitute paths in the graph (Filippova, 2010). We devise a parameterised shortest path algorithm that can be written as a generalised linear model in a joint space of word graphs and compressions. We use a large-margin approach to adapt parameterised edge weights to the data such that the shortest path is identical to the desired summary. Decoding during training is performed in polynomial time using loss augmented inference. Empirically, we compare our approach to the state-of-the-art in graph-based multi-sentence compression and observe significant improvements of about 7% in ROUGE F-measure and 8% in BLEU score, respectively.

KW - Informatics

KW - Business informatics

UR - http://www.scopus.com/inward/record.url?scp=84943749207&partnerID=8YFLogxK

UR - https://www.mendeley.com/catalogue/71fe9cf0-6be3-3329-b3d8-e329a11a5d88/

M3 - Article in conference proceedings

SN - 978-1-941643-26-6

T3 - COLING 2014 - 25th International Conference on Computational Linguistics, Proceedings of COLING 2014: Technical Papers

SP - 1636

EP - 1647

BT - COLING 2014 - 25th International Conference on Computational Linguistics, Proceedings of COLING 2014

PB - Association for Computational Linguistics (ACL)

CY - Dublin

T2 - 25th International Conference on Computational Linguistics - COLING 2014

Y2 - 23 August 2014 through 29 August 2014

ER -

Links