DFKI-LT - A Joint Syntactic-Semantic Representation for Recognizing Textual Relatedness

Rui Wang, Yi Zhang, GŁnter Neumann
A Joint Syntactic-Semantic Representation for Recognizing Textual Relatedness
3 Text Analysis Conference TAC 2009 WORKSHOP Notebook Papers and Results, Pages 1-7, National Institute of Standards and Technology (NIST), Gaithersburg, Maryland, USA, 9/2009
 
This paper describes our participation in the Recognizing Textual Entailment challenge (RTE-5) in the Text Analysis Conference (TAC 2009). Following the two-stage binary classification strategy, our focus this year is to recognize related Text-Hypothesis pairs instead of entailment pairs. In particular, we propose a joint syntactic-semantic representation to better capture the key information shared by the pair, and also apply a co-reference resolver to group cross-sentential mentionings of the same entities together. For the evaluation, we achieve 63.7% of accuracy on the three-way test, 68.5% on the entailment vs. non-entailment test, and 74.3% on the relatedness recognition. In both cases, we obtained the second best result among all teams. Based on the error analysis, we will work on differentiating entailment and contradiction in the future.
 
Files: BibTeX, DFKI.notebook.pdf