FBK Participation in the RTE-7 Main Task

This paper overviews FBK’s participation in the RTE-7 Main task organized within the Text Analysis Conference (TAC) 2011. Our participation is characterized by two main themes, namely: 1. The attempt to move from token-level overlap measures (i.e. a count of the terms in the hypothesis that can be mapped to terms in the Text), to phraselevel overlap measures that take into account a larger context to favour system’s precision; 2. The attempt to use paraphrase tables derived from parallel data as the main source of lexical knowledge for the mapping. In contrast with previous experiments over different datasets on one side, and the scores achieved over the RTE-7 DEV SET on the other side, our final results are lower than those obtained with the simpler token-overlap algorithm (41.90% Vs 44.1% Micro-Averaged F-measure). The motivations for this unexpected performance drop are still under investigation.