Spoken language understanding with kernels for syntactic/semantic structures

Alessandro Moschitti, Giuseppe Riccardi, Christian Raymond

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

14 Citations (Scopus)

Abstract

Automatic concept segmentation and labeling are the fundamental problems of Spoken Language Understanding in dialog systems. Such tasks are usually approached by using generative or discriminative models based on n-grams. As the uncertainty or ambiguity of the spoken input to dialog system increase, we expect to need dependencies beyond n-gram statistics. In this paper, a general purpose statistical syntactic parser is used to detect syntactic/semantic dependencies between concepts in order to increase the accuracy of sentence segmentation and concept labeling. The main novelty of the approach is the use of new tree kernel functions which encode syntactic/semantic structures in discriminative learning models. We experimented with Support Vector Machines and the above kernels on the standard ATIS dataset. The proposed algorithm automatically parses natural language text with off-the-shelf statistical parser and labels the syntactic (sub)trees with concept labels. The results show that the proposed model is very accurate and competitive with respect to state-of-theart models when combined with n-gram based models.

Original languageEnglish
Title of host publication2007 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2007, Proceedings
Pages183-188
Number of pages6
Publication statusPublished - 1 Dec 2007
Externally publishedYes
Event2007 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2007 - Kyoto, Japan
Duration: 9 Dec 200713 Dec 2007

Other

Other2007 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2007
CountryJapan
CityKyoto
Period9/12/0713/12/07

Fingerprint

Syntactics
Semantics
Labeling
Labels
Support vector machines
Statistics

Keywords

  • Kernel methods
  • Natural language processing
  • Spoken Language Understanding

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Software
  • Artificial Intelligence

Cite this

Moschitti, A., Riccardi, G., & Raymond, C. (2007). Spoken language understanding with kernels for syntactic/semantic structures. In 2007 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2007, Proceedings (pp. 183-188). [4430106]

Spoken language understanding with kernels for syntactic/semantic structures. / Moschitti, Alessandro; Riccardi, Giuseppe; Raymond, Christian.

2007 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2007, Proceedings. 2007. p. 183-188 4430106.

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

Moschitti, A, Riccardi, G & Raymond, C 2007, Spoken language understanding with kernels for syntactic/semantic structures. in 2007 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2007, Proceedings., 4430106, pp. 183-188, 2007 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2007, Kyoto, Japan, 9/12/07.
Moschitti A, Riccardi G, Raymond C. Spoken language understanding with kernels for syntactic/semantic structures. In 2007 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2007, Proceedings. 2007. p. 183-188. 4430106
Moschitti, Alessandro ; Riccardi, Giuseppe ; Raymond, Christian. / Spoken language understanding with kernels for syntactic/semantic structures. 2007 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2007, Proceedings. 2007. pp. 183-188
@inproceedings{71351ecee19241c0a22c5f1ba782f862,
title = "Spoken language understanding with kernels for syntactic/semantic structures",
abstract = "Automatic concept segmentation and labeling are the fundamental problems of Spoken Language Understanding in dialog systems. Such tasks are usually approached by using generative or discriminative models based on n-grams. As the uncertainty or ambiguity of the spoken input to dialog system increase, we expect to need dependencies beyond n-gram statistics. In this paper, a general purpose statistical syntactic parser is used to detect syntactic/semantic dependencies between concepts in order to increase the accuracy of sentence segmentation and concept labeling. The main novelty of the approach is the use of new tree kernel functions which encode syntactic/semantic structures in discriminative learning models. We experimented with Support Vector Machines and the above kernels on the standard ATIS dataset. The proposed algorithm automatically parses natural language text with off-the-shelf statistical parser and labels the syntactic (sub)trees with concept labels. The results show that the proposed model is very accurate and competitive with respect to state-of-theart models when combined with n-gram based models.",
keywords = "Kernel methods, Natural language processing, Spoken Language Understanding",
author = "Alessandro Moschitti and Giuseppe Riccardi and Christian Raymond",
year = "2007",
month = "12",
day = "1",
language = "English",
pages = "183--188",
booktitle = "2007 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2007, Proceedings",

}

TY - GEN

T1 - Spoken language understanding with kernels for syntactic/semantic structures

AU - Moschitti, Alessandro

AU - Riccardi, Giuseppe

AU - Raymond, Christian

PY - 2007/12/1

Y1 - 2007/12/1

N2 - Automatic concept segmentation and labeling are the fundamental problems of Spoken Language Understanding in dialog systems. Such tasks are usually approached by using generative or discriminative models based on n-grams. As the uncertainty or ambiguity of the spoken input to dialog system increase, we expect to need dependencies beyond n-gram statistics. In this paper, a general purpose statistical syntactic parser is used to detect syntactic/semantic dependencies between concepts in order to increase the accuracy of sentence segmentation and concept labeling. The main novelty of the approach is the use of new tree kernel functions which encode syntactic/semantic structures in discriminative learning models. We experimented with Support Vector Machines and the above kernels on the standard ATIS dataset. The proposed algorithm automatically parses natural language text with off-the-shelf statistical parser and labels the syntactic (sub)trees with concept labels. The results show that the proposed model is very accurate and competitive with respect to state-of-theart models when combined with n-gram based models.

AB - Automatic concept segmentation and labeling are the fundamental problems of Spoken Language Understanding in dialog systems. Such tasks are usually approached by using generative or discriminative models based on n-grams. As the uncertainty or ambiguity of the spoken input to dialog system increase, we expect to need dependencies beyond n-gram statistics. In this paper, a general purpose statistical syntactic parser is used to detect syntactic/semantic dependencies between concepts in order to increase the accuracy of sentence segmentation and concept labeling. The main novelty of the approach is the use of new tree kernel functions which encode syntactic/semantic structures in discriminative learning models. We experimented with Support Vector Machines and the above kernels on the standard ATIS dataset. The proposed algorithm automatically parses natural language text with off-the-shelf statistical parser and labels the syntactic (sub)trees with concept labels. The results show that the proposed model is very accurate and competitive with respect to state-of-theart models when combined with n-gram based models.

KW - Kernel methods

KW - Natural language processing

KW - Spoken Language Understanding

UR - http://www.scopus.com/inward/record.url?scp=43849091935&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=43849091935&partnerID=8YFLogxK

M3 - Conference contribution

SP - 183

EP - 188

BT - 2007 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2007, Proceedings

ER -