Study of using syntactic and semantic structures for concept segmentation and labeling

Iman Saleh, Shafiq Rayhan Joty, Lluis Marques, Alessandro Moschitti, Preslav Nakov, Scott Cyphers, Jim Glass

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

3 Citations (Scopus)

Abstract

This paper presents an empirical study on using syntactic and semantic information for Concept Segmentation and Labeling (CSL), a well-known component in spoken language understanding. Our approach is based on reranking N-best outputs from a state-of-the-art CSL parser. We perform extensive experimentation by comparing different tree-based kernels with a variety of representations of the available linguistic information, including semantic concepts, words, POS tags, shallow and full syntax, and discourse trees. The results show that the structured representation with the semantic concepts yields significant improvement over the base CSL parser, much larger compared to learning with an explicit feature vector representation. We also show that shallow syntax helps improve the results and that discourse relations can be partially beneficial.

Original languageEnglish
Title of host publicationCOLING 2014 - 25th International Conference on Computational Linguistics, Proceedings of COLING 2014: Technical Papers
PublisherAssociation for Computational Linguistics, ACL Anthology
Pages193-202
Number of pages10
ISBN (Electronic)9781941643266
Publication statusPublished - 2014
Externally publishedYes
Event25th International Conference on Computational Linguistics, COLING 2014 - Dublin, Ireland
Duration: 23 Aug 201429 Aug 2014

Other

Other25th International Conference on Computational Linguistics, COLING 2014
CountryIreland
CityDublin
Period23/8/1429/8/14

Fingerprint

semantics
syntax
discourse
spoken language
segmentation
Segmentation
Labeling
Syntactic Structure
Semantic Structure
linguistics
Syntax
learning
Semantic Information

ASJC Scopus subject areas

  • Language and Linguistics
  • Linguistics and Language

Cite this

Saleh, I., Rayhan Joty, S., Marques, L., Moschitti, A., Nakov, P., Cyphers, S., & Glass, J. (2014). Study of using syntactic and semantic structures for concept segmentation and labeling. In COLING 2014 - 25th International Conference on Computational Linguistics, Proceedings of COLING 2014: Technical Papers (pp. 193-202). Association for Computational Linguistics, ACL Anthology.

Study of using syntactic and semantic structures for concept segmentation and labeling. / Saleh, Iman; Rayhan Joty, Shafiq; Marques, Lluis; Moschitti, Alessandro; Nakov, Preslav; Cyphers, Scott; Glass, Jim.

COLING 2014 - 25th International Conference on Computational Linguistics, Proceedings of COLING 2014: Technical Papers. Association for Computational Linguistics, ACL Anthology, 2014. p. 193-202.

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

Saleh, I, Rayhan Joty, S, Marques, L, Moschitti, A, Nakov, P, Cyphers, S & Glass, J 2014, Study of using syntactic and semantic structures for concept segmentation and labeling. in COLING 2014 - 25th International Conference on Computational Linguistics, Proceedings of COLING 2014: Technical Papers. Association for Computational Linguistics, ACL Anthology, pp. 193-202, 25th International Conference on Computational Linguistics, COLING 2014, Dublin, Ireland, 23/8/14.
Saleh I, Rayhan Joty S, Marques L, Moschitti A, Nakov P, Cyphers S et al. Study of using syntactic and semantic structures for concept segmentation and labeling. In COLING 2014 - 25th International Conference on Computational Linguistics, Proceedings of COLING 2014: Technical Papers. Association for Computational Linguistics, ACL Anthology. 2014. p. 193-202
Saleh, Iman ; Rayhan Joty, Shafiq ; Marques, Lluis ; Moschitti, Alessandro ; Nakov, Preslav ; Cyphers, Scott ; Glass, Jim. / Study of using syntactic and semantic structures for concept segmentation and labeling. COLING 2014 - 25th International Conference on Computational Linguistics, Proceedings of COLING 2014: Technical Papers. Association for Computational Linguistics, ACL Anthology, 2014. pp. 193-202
@inproceedings{e44503107d24437181729ce66009caa3,
title = "Study of using syntactic and semantic structures for concept segmentation and labeling",
abstract = "This paper presents an empirical study on using syntactic and semantic information for Concept Segmentation and Labeling (CSL), a well-known component in spoken language understanding. Our approach is based on reranking N-best outputs from a state-of-the-art CSL parser. We perform extensive experimentation by comparing different tree-based kernels with a variety of representations of the available linguistic information, including semantic concepts, words, POS tags, shallow and full syntax, and discourse trees. The results show that the structured representation with the semantic concepts yields significant improvement over the base CSL parser, much larger compared to learning with an explicit feature vector representation. We also show that shallow syntax helps improve the results and that discourse relations can be partially beneficial.",
author = "Iman Saleh and {Rayhan Joty}, Shafiq and Lluis Marques and Alessandro Moschitti and Preslav Nakov and Scott Cyphers and Jim Glass",
year = "2014",
language = "English",
pages = "193--202",
booktitle = "COLING 2014 - 25th International Conference on Computational Linguistics, Proceedings of COLING 2014: Technical Papers",
publisher = "Association for Computational Linguistics, ACL Anthology",

}

TY - GEN

T1 - Study of using syntactic and semantic structures for concept segmentation and labeling

AU - Saleh, Iman

AU - Rayhan Joty, Shafiq

AU - Marques, Lluis

AU - Moschitti, Alessandro

AU - Nakov, Preslav

AU - Cyphers, Scott

AU - Glass, Jim

PY - 2014

Y1 - 2014

N2 - This paper presents an empirical study on using syntactic and semantic information for Concept Segmentation and Labeling (CSL), a well-known component in spoken language understanding. Our approach is based on reranking N-best outputs from a state-of-the-art CSL parser. We perform extensive experimentation by comparing different tree-based kernels with a variety of representations of the available linguistic information, including semantic concepts, words, POS tags, shallow and full syntax, and discourse trees. The results show that the structured representation with the semantic concepts yields significant improvement over the base CSL parser, much larger compared to learning with an explicit feature vector representation. We also show that shallow syntax helps improve the results and that discourse relations can be partially beneficial.

AB - This paper presents an empirical study on using syntactic and semantic information for Concept Segmentation and Labeling (CSL), a well-known component in spoken language understanding. Our approach is based on reranking N-best outputs from a state-of-the-art CSL parser. We perform extensive experimentation by comparing different tree-based kernels with a variety of representations of the available linguistic information, including semantic concepts, words, POS tags, shallow and full syntax, and discourse trees. The results show that the structured representation with the semantic concepts yields significant improvement over the base CSL parser, much larger compared to learning with an explicit feature vector representation. We also show that shallow syntax helps improve the results and that discourse relations can be partially beneficial.

UR - http://www.scopus.com/inward/record.url?scp=84926040770&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84926040770&partnerID=8YFLogxK

M3 - Conference contribution

SP - 193

EP - 202

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

PB - Association for Computational Linguistics, ACL Anthology

ER -