Question Answering using Sentence Parsing and Semantic Network Matching

The paper describes a question answering system for German called InSicht. All documents in the system are analyzed by a syntactico-semantic parser in order to represent each document sentence by a semantic network. A question sent to InSicht is parsed yielding its semantic network representation and its sentence type. The semantic network is expanded by applying equivalence rules, implicational rules, and concept variations based on semantic relations in computer lexicons and other knowledge sources. During the search stage, every semantic network generated for the question is matched with semantic networks for document sentences. If a match succeeds, an answer is generated from the matching semantic network for the supporting document. InSicht is evaluated on the QA@CLEF 2004 test set. A hierarchy of problem classes is proposed and a sample of suboptimally answered questions is annotated with these problem classes. Finally, some conclusions are drawn, main problems are identified, and directions for future work as suggested by these problems are indicated.

[1]  Hermann Helbig.  Die semantische Struktur natürlicher Sprache , 2001 .

[2]  Nancy Priest-Dorman Greg Ide,et al.  Corpus Encoding Standard (CES) , 2000 .

[3]  Hermann Helbig,et al.  Word Class Functions for Syntactic-Semantic Analysis , 1997 .

[4]  Sven Hartrumpf,et al.  Coreference resolution with syntactico-semantic rules and corpus statistics , 2001, CoNLL.

[5]  Daniel Marcu,et al.  Cross-Language Question Answering at the USC Information Sciences Institute , 2003, CLEF.

[6]  Rainer Osswald,et al.  Die Verwendung von GermaNet zur Pflege und Erweiterung des Computerlexikons HaGenLex , 2004, LDV Forum.

[7]  Carol Peters,et al.  Multilingual Information Access for Text, Speech and Images, 5th Workshop of the Cross-Language Evaluation Forum, CLEF 2004, Bath, UK, September 15-17, 2004, Revised Selected Papers , 2005, CLEF.

[8]  Michael M. Richter.  Die semantische Struktur natürlicher Sprache - Wissensrepräsentation mit MultiNet , 2002, Künstliche Intell..

[9]  Sven Hartrumpf,et al.  Hybrid disambiguation in natural language analysis , 2003 .

[10]  Hermann Helbig,et al.  Multilayered Extended Semantic Networks as a Language for Meaning Representation in NLP Systems , 2002, CICLing.

[11]  Sven Hartrumpf,et al.  The semantically based computer lexicon HaGenLex. Structure and technological environment , 2003 .

[12]  Sanda M. Harabagiu,et al.  The Role of Lexico-Semantic Feedback in Open-Domain Textual Question-Answering , 2001, ACL.

[13]  Sven Hartrumpf,et al.  University of Hagen at CLEF 2004: Indexing and Translating Concepts for the GIRT Task , 2004, CLEF.

[14]  Jiming Liu.  IEEE/WIC International Conference on Web Intelligence (WI 2003) : Halifax, Canada, October 13-17, 2003 : proceedings , 2003 .

[15]  Günter Neumann,et al.  Mining answers in German Web pages , 2003, Proceedings IEEE/WIC International Conference on Web Intelligence (WI 2003).