Re-Ranking models for spoken language understanding

Marco Dinarelli, Alessandro Moschitti, Giuseppe Riccardi

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

14 Citations (Scopus)

Abstract

Spoken Language Understanding aims at mapping a natural language spoken sentence into a semantic representation. In the last decade two main approaches have been pursued: generative and discriminative models. The former is more robust to overfitting whereas the latter is more robust to many irrelevant features. Additionally, the way in which these approaches encode prior knowledge is very different and their relative performance changes based on the task. In this paper we describe a machine learning framework where both models are used: a generative model produces a list of ranked hypotheses whereas a discriminative model based on structure kernels and Support Vector Machines, re-ranks such list. We tested our approach on the MEDIA corpus (human-machine dialogs) and on a new corpus (human-machine and human-human dialogs) produced in the European LUNA project. The results show a large improvement on the state-of-the-art in concept segmentation and labeling.

Original languageEnglish
Title of host publicationEACL 2009 - 12th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings
Pages202-210
Number of pages9
Publication statusPublished - 1 Dec 2009
Externally publishedYes
Event12th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2009 - Athens, Greece
Duration: 30 Mar 20093 Apr 2009

Other

Other12th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2009
CountryGreece
CityAthens
Period30/3/093/4/09

Fingerprint

spoken language
ranking
dialogue
semantics
Spoken Language Understanding
Ranking
knowledge
learning
performance
Generative

ASJC Scopus subject areas

  • Language and Linguistics
  • Linguistics and Language

Cite this

Dinarelli, M., Moschitti, A., & Riccardi, G. (2009). Re-Ranking models for spoken language understanding. In EACL 2009 - 12th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings (pp. 202-210)

Re-Ranking models for spoken language understanding. / Dinarelli, Marco; Moschitti, Alessandro; Riccardi, Giuseppe.

EACL 2009 - 12th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings. 2009. p. 202-210.

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

Dinarelli, M, Moschitti, A & Riccardi, G 2009, Re-Ranking models for spoken language understanding. in EACL 2009 - 12th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings. pp. 202-210, 12th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2009, Athens, Greece, 30/3/09.
Dinarelli M, Moschitti A, Riccardi G. Re-Ranking models for spoken language understanding. In EACL 2009 - 12th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings. 2009. p. 202-210
Dinarelli, Marco ; Moschitti, Alessandro ; Riccardi, Giuseppe. / Re-Ranking models for spoken language understanding. EACL 2009 - 12th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings. 2009. pp. 202-210
@inproceedings{fceb0ac3582f4733ab2c1ceca2da13ac,
title = "Re-Ranking models for spoken language understanding",
abstract = "Spoken Language Understanding aims at mapping a natural language spoken sentence into a semantic representation. In the last decade two main approaches have been pursued: generative and discriminative models. The former is more robust to overfitting whereas the latter is more robust to many irrelevant features. Additionally, the way in which these approaches encode prior knowledge is very different and their relative performance changes based on the task. In this paper we describe a machine learning framework where both models are used: a generative model produces a list of ranked hypotheses whereas a discriminative model based on structure kernels and Support Vector Machines, re-ranks such list. We tested our approach on the MEDIA corpus (human-machine dialogs) and on a new corpus (human-machine and human-human dialogs) produced in the European LUNA project. The results show a large improvement on the state-of-the-art in concept segmentation and labeling.",
author = "Marco Dinarelli and Alessandro Moschitti and Giuseppe Riccardi",
year = "2009",
month = "12",
day = "1",
language = "English",
isbn = "9781932432169",
pages = "202--210",
booktitle = "EACL 2009 - 12th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings",

}

TY - GEN

T1 - Re-Ranking models for spoken language understanding

AU - Dinarelli, Marco

AU - Moschitti, Alessandro

AU - Riccardi, Giuseppe

PY - 2009/12/1

Y1 - 2009/12/1

N2 - Spoken Language Understanding aims at mapping a natural language spoken sentence into a semantic representation. In the last decade two main approaches have been pursued: generative and discriminative models. The former is more robust to overfitting whereas the latter is more robust to many irrelevant features. Additionally, the way in which these approaches encode prior knowledge is very different and their relative performance changes based on the task. In this paper we describe a machine learning framework where both models are used: a generative model produces a list of ranked hypotheses whereas a discriminative model based on structure kernels and Support Vector Machines, re-ranks such list. We tested our approach on the MEDIA corpus (human-machine dialogs) and on a new corpus (human-machine and human-human dialogs) produced in the European LUNA project. The results show a large improvement on the state-of-the-art in concept segmentation and labeling.

AB - Spoken Language Understanding aims at mapping a natural language spoken sentence into a semantic representation. In the last decade two main approaches have been pursued: generative and discriminative models. The former is more robust to overfitting whereas the latter is more robust to many irrelevant features. Additionally, the way in which these approaches encode prior knowledge is very different and their relative performance changes based on the task. In this paper we describe a machine learning framework where both models are used: a generative model produces a list of ranked hypotheses whereas a discriminative model based on structure kernels and Support Vector Machines, re-ranks such list. We tested our approach on the MEDIA corpus (human-machine dialogs) and on a new corpus (human-machine and human-human dialogs) produced in the European LUNA project. The results show a large improvement on the state-of-the-art in concept segmentation and labeling.

UR - http://www.scopus.com/inward/record.url?scp=84891599235&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84891599235&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9781932432169

SP - 202

EP - 210

BT - EACL 2009 - 12th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings

ER -