Using Paraphrases and Lexical Semantics to Improve the Accuracy and the Robustness of Supervised Models in Situated Dialogue Systems

Claire Gardent 1 Lina Maria Rojas Barahona 1
1 SYNALP - Natural Language Processing : representations, inference and semantics
LORIA - NLPKD - Department of Natural Language Processing & Knowledge Discovery
Abstract : This paper explores to what extent lemmatisation, lexical resources, distributional semantics and paraphrases can increase the accuracy of supervised models for dialogue management. The results suggest that each of these factors can help improve performance but that the impact will vary depending on their combination and on the evaluation mode.
Complete list of metadatas

Cited literature [11 references]  Display  Hide  Download

https://hal.inria.fr/hal-00905405
Contributor : Lina Maria Rojas Barahona <>
Submitted on : Monday, November 18, 2013 - 11:21:23 AM
Last modification on : Tuesday, December 18, 2018 - 4:38:01 PM
Long-term archiving on : Saturday, April 8, 2017 - 12:18:39 AM

File

D13-1076.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00905405, version 1

Collections

Citation

Claire Gardent, Lina Maria Rojas Barahona. Using Paraphrases and Lexical Semantics to Improve the Accuracy and the Robustness of Supervised Models in Situated Dialogue Systems. Conference on Empirical Methods in Natural Language Processing, SIGDAT, the Association for Computational Linguistics special interest group on linguistic data and corpus-based approaches to NLP, Oct 2013, Seattle, United States. pp.808-813. ⟨hal-00905405⟩

Share

Metrics

Record views

491

Files downloads

497