Computational Linguistics Colloquium

Thursday, 14 February, 16:15
Conference Room, Building C7 4

Containment, Exclusion, and Implicativity: A Model of Natural Logic for Textual Inference

We propose an approach to textual inference based on a model of natural logic, which identifies valid inferences by their lexical and syntactic features, without full semantic interpretation. This model offers a middle ground between systems based on approximate matching, which are robust but imprecise, and approaches based on logical deduction, which are precise but brittle. We greatly extend past work in natural logic, which has focused solely on semantic containment and monotonicity, to incorporate both semantic exclusion and implicativity. Our system decomposes an inference problem into a sequence of atomic edits linking premise to hypothesis; predicts a lexical entailment relation for each edit using a statistical classifier; propagates these relations upward through a syntax tree according to semantic properties of intermediate nodes; and composes the resulting entailment relations across the edit sequence. We evaluate our system on the FraCaS test suite and on RTE3 data; on FraCaS we achieve a 27% reduction in error from previous work.

If you would like to meet with the speaker, please contact Stefan Thater.