Position-Aligned Translation Model for Citation Recommendation
Jing He (peaceful (point) he <at> gmail (point) com)
Wednesday 3 April 2013 at 11:30 AM
Salle 3195, Pavillon André-Aisenstadt
The goal of a citation recommendation system is to suggest some references for a snippet in an article or a book, and this is very useful for both authors and the readers. The citation recommendation problem can be cast as an information retrieval problem, in which the query is the snippet from an article, and the relevant documents are the cited articles. In reality, the citation snippet and the cited articles may be described in different terms, and it leads difficulty in the retrieval. Translation model is very useful in bridging the vocabulary gap between queries and documents in information retrieval. It can be trained on a collection of query and document pairs, which are assumed to be parallel. However, such training data contains much noise: a relevant document usually contains some relevant parts along with irrelevant ones. Particularly, the citation snippet may only mention only some parts of the cited article’s content. To cope with this problem, in this talk, we propose a method to train translation models on such noisy data, called positionaligned translation model. This model tries to align the query to the most relevant parts of the document, so that the estimated translation probabilities could rely more on them. We test this model in a citation recommendation task for scientific papers. Our experiments show that the proposed method can significantly improve the previous retrieval methods based on the translation model.
Follow this link to subscribe to future RALI-OLST announcements.
See all the weekly talks for the year:1991 1992 1993 1994 1995 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023