Tree Edit Models for Recognizing Textual Entailments, Paraphrases, and Answers to Questions

We describe tree edit models for representing sequences of tree transformations involving complex reordering phenomena and demonstrate that they offer a simple, intuitive, and effective method for modeling pairs of semantically related sentences. To efficiently extract sequences of edits, we employ a tree kernel as a heuristic in a greedy search routine. We describe a logistic regression model that uses 33 syntactic features of edit sequences to classify the sentence pairs. The approach leads to competitive performance in recognizing textual entailment, paraphrase identification, and answer selection for question answering.

• Type: Journal
• Year: 2010
• Where: NAACL
• Authors: Michael Heilman, Noah A. Smith
• Keywords: Complex Reordering Phenomena, Computational Linguistics, Greedy Search Routine, NAACL 2010, Tree Edit Models