RTE6 - Call for Resources

A study on the knowledge resources used in Textual Entailment was started with the ablation tests carried out on the RTE5 Main task submissions, which gave a hint about the impact of knowledge resources on TE system performances. Given the interest raised by this new initiative, the investigation of knowledge resources will be carried on also in RTE6.

In order to help the research, all the participants are invited to contribute, sharing their own resources with the RTE community. Making the resources available to be used by other systems has several advantages. On the one hand, it helps improve the TE technology; on the other hand, it offers an opportunity to further test and evaluate the resource.

Here below the new resources already available for RTE6 are listed.

New resources available!

Resource	Type	Author	Brief description
Normalized Google Distance (RTE3&RTE4)	Word Pair Co-occurrence	Saarland University	Co-occurrence of the word pairs in RTE3 and RTE4 using Normalized Google Distance (Cilibrasi and Vitanyi, 2004). The word pairs are all the possible combinations of content words in T and H. In practice, we used Yahoo! as the search engine.
Normalized Google Distance (RTE5)	Word Pair Co-occurrence	Saarland University	Co-occurrence of the word pairs in RTE3 and RTE4 using Normalized Google Distance (Cilibrasi and Vitanyi, 2004). The word pairs are all the possible combinations of content words in T and H. In practice, we used Yahoo! as the search engine.
WikiRules!	Lexical Reference rule-base	Bar-Ilan University	Extraction of lexical reference rules from the text body (first sentence) and from metadata (links, redirects, parentheses) of Wikipedia

   Return to RTE Knowledge Resources