论文信息 - Topic Indexing and Retrieval for Factoid QA

Topic Indexing and Retrieval for Factoid QA

The method of Topic Indexing and Retrieval for QA persented in this paper enables fast and efficent QA for questions with named entity answers. This is achieved by identifying all possible named entity answers in a corpus off-line and gathering all possible evidence for their direct retrieval as answer candidates using standard IR techniques. An evaluation of this method on 377 TREC questions produced a score of 0.342 in Accuracy and 0.413 in Mean Reciprocal Rank (MRR).

Kisuh Ahn | Bonnie Lynn Webber

[1] Jimmy J. Lin,et al. Omnibase: Uniform Access to Heterogeneous Data for Question Answering , 2002, NLDB.

[2] William John Teahan,et al. Bangor at TREC 2004: Question Answering Track , 2004, TREC.

[3] James P. Callan,et al. Experiments Using the Lemur Toolkit , 2001, TREC.

[4] F. Wilcoxon. Individual Comparisons by Ranking Methods , 1945 .

[5] Dan Roth,et al. Learning Question Classifiers , 2002, COLING.

[6] Eduard H. Hovy,et al. Offline Strategies for Online Question Answering: Answering Questions Before They Are Asked , 2003, ACL.

[7] Dragomir R. Radev,et al. The Use of Predictive Annotation for Question Answering in TREC8 , 1999, TREC.

[8] Jungyun Seo,et al. MAYA: A Fast Question-answering System Based on a Predictive Answer Indexer , 2001, ACL 2001.

[9] Fabian M. Suchanek,et al. Yago: A Core of Semantic Knowledge Unifying WordNet and Wikipedia , 2007 .

[10] Valentin Jijkoun,et al. Information Extraction for Question Answering: Improving Recall Through Syntactic Patterns , 2004, COLING.

[11] Jimmy J. Lin,et al. REXTOR: A System for Generating Relations from Natural Language , 2000 .

[12] James R. Curran,et al. Language Independent NER using a Maximum Entropy Tagger , 2003, CoNLL.

[13] Gerhard Weikum,et al. WWW 2007 / Track: Semantic Web Session: Ontologies ABSTRACT YAGO: A Core of Semantic Knowledge , 2022 .