Symposium on Machine Learning in Speech and Language Processing (MLSLP)
Bellevue, WA, USA
In this paper, we consider the problem of cross-document co-reference (CDC). Existing approaches tend to treat CDC as an information retrieval based problem and use features such as TF-IDF cosine similarity to cluster documents and/or co-reference chains. We augmented these features with features based on biographical attributes, such as occupation, nationality, gender, etc., obtained by using semi-supervised attribute extraction models. Our results suggest that the addition of these features boosts the performance of our CDC system considerably. The extraction of such specific attributes allows us to use features, such as semantic similarity, mutual information and approximate name similarity which have not been used so far for CDC with traditional bag-of-words models. Our system achieves F0.5 scores of 0.82 and 0.81 on the WePS-1 and WePS-2 datasets, which rival the best reported scores for this problem.
Bibliographic reference. Shah, Rushin / Lin, Bo / Rosa, Kevin Dela / Gershman, Anatole / Frederking, Robert (2011): "Improving cross-document co-reference with semi-supervised information extraction modelsi", In MLSLP-2011, 21-25.