Learning of graph-based question answering rules

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contributionpeer-review


In this paper we present a graph-based approach to question answering. The method assumes a graph representation of question sentences and text sentences. Question answering rules are automatically learnt from a training corpus of questions and answer sentences with the answer annotated. The method is independent from the graph representation formalism chosen. A particular example is presented that uses a specific graph representation of the logical contents of sentences.
Original languageEnglish
Title of host publicationProceedings of TextGraphs
Subtitle of host publicationGraph-based Algorithms for Natural Language Processing, Workshop at HLT/NAACL 2006
EditorsRada Mihalcea, Dragomir Radev
Place of PublicationUnited States
PublisherAssociation for Computational Linguistics
Number of pages8
ISBN (Print)1932432647
Publication statusPublished - 2006
EventTextGraphs : Graph-based Algorithms for Natural Language Processing Workshop - New York
Duration: 9 Jun 20069 Jun 2006


WorkshopTextGraphs : Graph-based Algorithms for Natural Language Processing Workshop
CityNew York

Cite this