The retrieval of sentences is a core task within Information Retrieval. In this poster we employ a Language Model that incorporates a prior which encodes the importance of sentences within the retrieval model. Then, in a set of comprehensive experiments using the TREC Novelty Tracks, we show that including this prior substantially improves retrieval effectiveness, and significantly outperforms the current state of the art in sentence retrieval.
|Title of host publication||SIGIR '10 Proceedings of the 33rd International ACM SIGIR Conference on Research and Development in Information Retrieval|
|Place of Publication||New York, NY, USA|
|Number of pages||2|
|Publication status||Published - 19 Jul 2010|
- language model
- sentence retrieval
Azzopardi, L., Fernández, R. T., & Losada, D. E. (2010). Improving sentence retrieval with an importance prior. In SIGIR '10 Proceedings of the 33rd International ACM SIGIR Conference on Research and Development in Information Retrieval (pp. 779-780). New York, NY, USA. https://doi.org/10.1145/1835449.1835612