Integrating Linguistic Knowledge in Passage Retrieval for Question Answering

In this paper we investigate the use of linguistic knowledge in passage retrieval as part of an open-domain question answering system. We use annotation produced by a deep syntactic dependency parser for Dutch, Alpino, to extract various kinds of linguistic features and syntactic units to be included in a multi-layer index. Similar annotation is produced for natural language questions to be answered by the system. From this we extract query terms to be sent to the enriched retrieval index. We use a genetic algorithm to optimize the selection of features and syntactic units to be included in a query. This algorithm is also used to optimize further parameters such as keyword weights. The system is trained on questions from the competition on Dutch question answering within the Cross-Language Evaluation Forum (CLEF). We could show an improvement of about 15% in mean total reciprocal rank compared to traditional information retrieval using plain text keywords (including stemming and stop word removal).