Hypotheses selection for re-ranking semantic annotations

Marco Dinarelli, Alessandro Moschitti, Giuseppe Riccardi

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

3 Citations (Scopus)

Abstract

Discriminative reranking has been successfully used for several tasks of Natural Language Processing (NLP). Recently it has been applied also to Spoken Language Understanding, imrpoving state-of-the-art for some applications. However, such proposed models can be further improved by considering: (i) a better selection of the initial nbest hypotheses to be re-ranked and (ii) the use of a strategy that decides when the reranking model should be used, i.e. in some cases only the basic approach should be applied. In this paper, we apply a semantic inconsistency metric to select the n-best hypotheses from a large set generated by an SLU basic system. Then we apply a state-of-the-art re-ranker based on the Partial Tree Kernel (PTK), which encodes SLU hypotheses in Support Vector Machines (SVM) with complex structured features. Finally, we apply a decision model based on confidence values to select between the first hypothesis provided by the basic SLU model and the first hypothesis provided by the re-ranker. We show the effectiveness of our approach presenting comparative results obtained by reranking hypotheses generated by two very different models: a simple Stochastic Language Model encoded in Finite State Machines (FSM) and a Conditional Random Field (CRF) model. We evaluate our approach on the French MEDIA corpus and on an Italian corpus acquired in the European Project LUNA. The results show a significant improvement with respect to the current state-of-the-art and previous re-ranking models.

Original languageEnglish
Title of host publication2010 IEEE Workshop on Spoken Language Technology, SLT 2010 - Proceedings
Pages407-411
Number of pages5
DOIs
Publication statusPublished - 1 Dec 2010
Externally publishedYes
Event2010 IEEE Workshop on Spoken Language Technology, SLT 2010 - Berkeley, CA, United States
Duration: 12 Dec 201015 Dec 2010

Other

Other2010 IEEE Workshop on Spoken Language Technology, SLT 2010
CountryUnited States
CityBerkeley, CA
Period12/12/1015/12/10

    Fingerprint

Keywords

  • Discriminative reranking
  • Kernel methods
  • Spoken language understanding

ASJC Scopus subject areas

  • Language and Linguistics

Cite this

Dinarelli, M., Moschitti, A., & Riccardi, G. (2010). Hypotheses selection for re-ranking semantic annotations. In 2010 IEEE Workshop on Spoken Language Technology, SLT 2010 - Proceedings (pp. 407-411). [5700887] https://doi.org/10.1109/SLT.2010.5700887