Semantic kernels for semantic parsing

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

5 Citations (Scopus)

Abstract

We present an empirical study on the use of semantic information for Concept Segmentation and Labeling (CSL), which is an important step for semantic parsing. We represent the alternative analyses output by a state-of-the-art CSL parser with tree structures, which we rerank with a classifier trained on two types of semantic tree kernels: one processing structures built with words, concepts and Brown clusters, and another one using semantic similarity among the words composing the structure. The results on a corpus from the restaurant domain show that our semantic kernels exploiting similarity measures outperform state-of-the-art rerankers.

Original languageEnglish
Title of host publicationEMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference
PublisherAssociation for Computational Linguistics (ACL)
Pages436-442
Number of pages7
ISBN (Print)9781937284961
Publication statusPublished - 2014
Event2014 Conference on Empirical Methods in Natural Language Processing, EMNLP 2014 - Doha, Qatar
Duration: 25 Oct 201429 Oct 2014

Other

Other2014 Conference on Empirical Methods in Natural Language Processing, EMNLP 2014
CountryQatar
CityDoha
Period25/10/1429/10/14

Fingerprint

Semantics
Labeling
Classifiers
Processing

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Computer Vision and Pattern Recognition
  • Information Systems

Cite this

Saleh, I., Moschitti, A., Nakov, P., Marques, L., & Rayhan Joty, S. (2014). Semantic kernels for semantic parsing. In EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference (pp. 436-442). Association for Computational Linguistics (ACL).

Semantic kernels for semantic parsing. / Saleh, Iman; Moschitti, Alessandro; Nakov, Preslav; Marques, Lluis; Rayhan Joty, Shafiq.

EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference. Association for Computational Linguistics (ACL), 2014. p. 436-442.

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

Saleh, I, Moschitti, A, Nakov, P, Marques, L & Rayhan Joty, S 2014, Semantic kernels for semantic parsing. in EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference. Association for Computational Linguistics (ACL), pp. 436-442, 2014 Conference on Empirical Methods in Natural Language Processing, EMNLP 2014, Doha, Qatar, 25/10/14.
Saleh I, Moschitti A, Nakov P, Marques L, Rayhan Joty S. Semantic kernels for semantic parsing. In EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference. Association for Computational Linguistics (ACL). 2014. p. 436-442
Saleh, Iman ; Moschitti, Alessandro ; Nakov, Preslav ; Marques, Lluis ; Rayhan Joty, Shafiq. / Semantic kernels for semantic parsing. EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference. Association for Computational Linguistics (ACL), 2014. pp. 436-442
@inproceedings{14a947a052874be0acf8879c8b84c3a8,
title = "Semantic kernels for semantic parsing",
abstract = "We present an empirical study on the use of semantic information for Concept Segmentation and Labeling (CSL), which is an important step for semantic parsing. We represent the alternative analyses output by a state-of-the-art CSL parser with tree structures, which we rerank with a classifier trained on two types of semantic tree kernels: one processing structures built with words, concepts and Brown clusters, and another one using semantic similarity among the words composing the structure. The results on a corpus from the restaurant domain show that our semantic kernels exploiting similarity measures outperform state-of-the-art rerankers.",
author = "Iman Saleh and Alessandro Moschitti and Preslav Nakov and Lluis Marques and {Rayhan Joty}, Shafiq",
year = "2014",
language = "English",
isbn = "9781937284961",
pages = "436--442",
booktitle = "EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference",
publisher = "Association for Computational Linguistics (ACL)",

}

TY - GEN

T1 - Semantic kernels for semantic parsing

AU - Saleh, Iman

AU - Moschitti, Alessandro

AU - Nakov, Preslav

AU - Marques, Lluis

AU - Rayhan Joty, Shafiq

PY - 2014

Y1 - 2014

N2 - We present an empirical study on the use of semantic information for Concept Segmentation and Labeling (CSL), which is an important step for semantic parsing. We represent the alternative analyses output by a state-of-the-art CSL parser with tree structures, which we rerank with a classifier trained on two types of semantic tree kernels: one processing structures built with words, concepts and Brown clusters, and another one using semantic similarity among the words composing the structure. The results on a corpus from the restaurant domain show that our semantic kernels exploiting similarity measures outperform state-of-the-art rerankers.

AB - We present an empirical study on the use of semantic information for Concept Segmentation and Labeling (CSL), which is an important step for semantic parsing. We represent the alternative analyses output by a state-of-the-art CSL parser with tree structures, which we rerank with a classifier trained on two types of semantic tree kernels: one processing structures built with words, concepts and Brown clusters, and another one using semantic similarity among the words composing the structure. The results on a corpus from the restaurant domain show that our semantic kernels exploiting similarity measures outperform state-of-the-art rerankers.

UR - http://www.scopus.com/inward/record.url?scp=84961361408&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84961361408&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9781937284961

SP - 436

EP - 442

BT - EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference

PB - Association for Computational Linguistics (ACL)

ER -