Publication

SURFACE LANGUAGE MODELS FOR DISCOVERING TEMPORALLY ANCHORED DEFINITIONS ON THE WEB - Producing Chronologies as Answers to Definition Questions

Alejandro Figueroa

In: WEBIST 2010 - Proceedings of the Fifth International Conference on Web Information Systems and Technologies. International Conference on Web Information Systems and Technologies (WEBIST-2010) 6th May 6-9 Valencia Spain INSTICC Press 4/2010.

Abstract

This work presents a data-driven definition question answering (QA) system that outputs a set of temporally anchored definitions as answers. This system builds surface language models on top of a corpus automatically acquired from Wikipedia abstracts, and ranks answer candidates in agreement with these models afterwards. Additionally, this study deals at greater length with the impact of several surface features in the ranking of temporally anchored answers.

Projekte

webist2010_v2.pdf (pdf, 96 KB)

German Research Center for Artificial Intelligence
Deutsches Forschungszentrum für Künstliche Intelligenz