Parsing enhancing of the conversational module for a service robot : Différence entre versions

De wikiRcln
Aller à : navigation, rechercher
(2018)
Ligne 28 : Ligne 28 :
 
* Ivette Vélez (IIMAS/UNAM)
 
* Ivette Vélez (IIMAS/UNAM)
 
* Jorge García Flores (LIPN/UP13)
 
* Jorge García Flores (LIPN/UP13)
 +
 +
==References==
 +
<references/>

Version du 17 mai 2017 à 17:58

Abstract

The goal of the project is to improve the syntactic parser of the Golem service robot [1]

[2]


. The parsing module takes its imput from the Automatic Speech Recognition (ASR), which produces a text line to be parsed. The output of the parser is a SitLog command which triggers an action in the robot.

Work plan

2017

  1. Create an evaluation testbed for the parser based on (Doostdar et al., 20907)[3].
  2. Train a machine learning model to generate DGC[4]

2018

  1. Transform the DGC-based (Definite Clause Grammar) parser into a CCG (Combinatorial Categorial Grammar)[5][6] based parser
  2. Evaluate Google's Parsey MacParseface[7] with the service robot oriented parsing evaluation testbed.

2019

  1. Integrate Parsey MacParceface

Team

  • Luis Pineda (IIMAS/UNAM)
  • Ivette Vélez (IIMAS/UNAM)
  • Jorge García Flores (LIPN/UP13)

References

  1. Doostdar M., Schiffer S., Lakemeyer G. (2009) A Robust Speech Regognition System for Service-Robots Application. In: Iocchi L., Matsubara H., Weitzenfeld A., Zhou C. (eds) RoboCup 2008: Robot Soccer World Cup XII. RoboCup 2008. Lecture Notes in Computer Science, vol 5399. Springer, Berlin, Heidelberg
  2. Tarau, P. and Figa, E.: Knowledge Based Conversational Agents and Virtual Storytelling. In Proceedings of the 2004 ACM Symposium on Applied Computing (Nicosia, Cyprus, March 14 - 17, 004). SAC '04. ACM Press, New York, NY, 39-44. (2004)
  3. R. Cantrell, M. Scheutz, P. Schermerhorn and X. Wu, "Robust spoken instruction understanding for HRI," 2010 5th ACM/IEEE International Conference on Human-Robot Interaction (HRI), Osaka, 2010, pp. 275-282.
  4. M. Eppe, S. Trott and J. Feldman, "Exploiting Deep Semantics and Compositionality of Natural Language for Human-Robot-Interaction," 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Daejeon, 2016, pp. 731-738.
  5. [https://research.googleblog.com/2016/05/announcing-syntaxnet-worlds-most.html Announcing SyntaxNet: The World’s Most Accurate Parser Goes Open Source]