Browse DORAS
Browse Theses
Search
Latest Additions
Creative Commons License
Except where otherwise noted, content on this site is licensed for use under a:

Efficient question answering with question decomposition and multiple answer streams

Hartrumpf, Sven and Glöckner, Ingo and Leveling, Johannes (2009) Efficient question answering with question decomposition and multiple answer streams. In: CLEF 2009, 30 Sept - 2 Oct. 2009, Corfu, Greece.

Full text available as:

[img]PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
111Kb

Abstract

The German question answering (QA) system IRSAW (formerly: InSicht) participated in QA@CLEF for the fth time. IRSAW was introduced in 2007 by integrating the deep answer producer InSicht, several shallow answer producers, and a logical validator. InSicht builds on a deep QA approach: it transforms documents to semantic representations using a parser, draws inferences on semantic representations with rules, and matches semantic representations derived from questions and documents. InSicht was improved for QA@CLEF 2008 mainly in the following two areas. The coreference resolver was trained on question series instead of newspaper texts in order to be better applicable for follow-up questions. Questions are decomposed by several methods on the level of semantic representations. On the shallow processing side, the number of answer producers was increased from two to four by adding FACT, a fact index, and SHASE, a shallow semantic network matcher. The answer validator introduced in 2007 was replaced by the faster RAVE validator designed for logic-based answer validation under time constraints. Using RAVE for merging the results of the answer producers, monolingual German runs and bilingual runs with source language English and Spanish were produced by applying the machine translation web service Promt. An error analysis shows the main problems for the precision-oriented deep answer producer InSicht and the potential offered by the recall-oriented shallow answer producers.

Item Type:Conference or Workshop Item (Paper)
Event Type:Workshop
Refereed:Yes
Uncontrolled Keywords:question answering; QA; question decomposition; IRSAW
Subjects:Computer Science > Information retrieval
DCU Faculties and Centres:Research Initiatives and Centres > Centre for Next Generation Localisation (CNGL)
Published in:Multilingual Information Access Evaluation I. Text Retrieval Experiments. Lecture Notes in Computer Science 6241. Springer-Verlag.
Publisher:Springer-Verlag
Official URL:http://www.springerlink.com/content/w1x346822834r414/
Copyright Information:© 2009 Springer-Verlag. The original publication is available at www.springerlink.com
Use License:This item is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 3.0 License. View License
ID Code:16441
Deposited On:22 Jul 2011 14:56 by Shane Harper. Last Modified 22 Jul 2011 14:56

Download statistics

Archive Staff Only: edit this record