Probabilistic Tree-Edit Models with Structured Latent Variables for Textual Entailment and Question Answering

This work captures the alignment by using a novel probabilistic model that models tree-edit operations on dependency parse trees and treats alignments as structured latent variables, and offers a principled framework for incorporating complex linguistic features.

Abstract

A range of Natural Language Processing tasks involve making judgments about the semantic relatedness of a pair of sentences, such as Recognizing Textual Entailment (RTE) and answer selection for Question Answering (QA). A key challenge that these tasks face in common is the lack of explicit alignment annotation between a sentence pair. We capture the alignment by using a novel probabilistic model that models tree-edit operations on dependency parse trees. Unlike previous tree-edit models which require a separate alignment-finding phase and resort to ad-hoc distance metrics, our method treats alignments as structured latent variables, and offers a principled framework for incorporating complex linguistic features. We demonstrate the robustness of our model by conducting experiments for RTE and QA, and show that our model performs competitively on both tasks with the same set of general features. 1