Building an end-to-end text reading system based on a packed representation

Authors:
Doo Soon Kim;Ken Barker;Bruce Porter
Affiliations:
University of Texas, Austin, TX;University of Texas, Austin, TX;University of Texas, Austin, TX
Venue:
FAM-LbR '10 Proceedings of the NAACL HLT 2010 First International Workshop on Formalisms and Methodology for Learning by Reading
Year:
2010

Citing 6
Cited 1

Efficient Parsing for Natural Language: A Fast Algorithm for Practical Systems

Efficient Parsing for Natural Language: A Fast Algorithm for Practical Systems
Semantic construction from parse forests

COLING '96 Proceedings of the 16th conference on Computational linguistics - Volume 2
Accurate unlexicalized parsing

ACL '03 Proceedings of the 41st Annual Meeting on Association for Computational Linguistics - Volume 1
SenseRelate::TargetWord: a generalized framework for word sense disambiguation

ACLdemo '05 Proceedings of the ACL 2005 on Interactive poster and demonstration sessions
Large-scale extraction and use of knowledge from text

Proceedings of the fifth international conference on Knowledge capture
The necessity of syntactic parsing for semantic role labeling

IJCAI'05 Proceedings of the 19th international joint conference on Artificial intelligence

Exploiting paraphrases and deferred sense commitment to interpret questions more reliably

COLING '10 Proceedings of the 23rd International Conference on Computational Linguistics: Posters

Quantified Score

Hi-index	0.00

Visualization

Abstract

We previously proposed a packed graphical representation to succinctly represent a huge number of alternative semantic representations of a given sentence. We also showed that this representation could improve text interpretation accuracy considerably because the system could postpone resolving ambiguity until more evidence accumulates. This paper discusses our plan to build an end-to-end text reading system based on our packed representation.