Combining Deterministic Dependency Parsing and Linear Classification for Robust RTE

Alexander Volokh, Günter Neumann, Bogdan Sacaleanu

In: Third Text Analysis Conference. Text Analysis Conference (TAC-10) November 14-15 Gaithersburg MD United States NIST 2010.


We present a robust RTE approach which is built as one module incorporating all possible knowledge sources in form of different features. This way we can easily include or remove´knowledge sources which are involved into the process of judging the entailment relation. We perform numerous tests in which we analyse the contribution of different types of features based on word forms, structural information, lexical semantics and named entity recognition to this process. The core of our system is our own deterministic dependency parser MDParser, which is based on a fast linear classification approach. We use the RTE6 challenge as an opportunity to evaluate its performance in a real-world application against another state of the art parser MaltParser. In our official submissions we achieve an f-score of 39.81 with MaltParser and 38.26 with MDParser. However, the parsing speed with MDParser is 26 times higher.


Weitere Links

Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence