A phrase-based alignment model for natural language inference

  • Authors:
  • Bill MacCartney;Michel Galley;Christopher D. Manning

  • Affiliations:
  • Stanford University;Stanford University;Stanford University

  • Venue:
  • EMNLP '08 Proceedings of the Conference on Empirical Methods in Natural Language Processing
  • Year:
  • 2008

Quantified Score

Hi-index 0.00

Visualization

Abstract

The alignment problem---establishing links between corresponding phrases in two related sentences---is as important in natural language inference (NLI) as it is in machine translation (MT). But the tools and techniques of MT alignment do not readily transfer to NLI, where one cannot assume semantic equivalence, and for which large volumes of bitext are lacking. We present a new NLI aligner, the MANLI system, designed to address these challenges. It uses a phrase-based alignment representation, exploits external lexical resources, and capitalizes on a new set of supervised training data. We compare the performance of MANLI to existing NLI and MT aligners on an NLI alignment task over the well-known Recognizing Textual Entailment data. We show that MANLI significantly outperforms existing aligners, achieving gains of 6.2% in F1 over a representative NLI aligner and 10.5% over GIZA++.