Entailment Graph Learning with Textual Entailment and Soft Transitivity

TL;DR

This paper introduces EGT2, a two-stage method that leverages textual entailment recognition and soft transitivity constraints to improve entailment graph learning, addressing sparsity and reliability issues in predicate entailment modeling.

Contribution

The paper proposes a novel two-stage approach combining textual entailment recognition with soft transitivity constraints to enhance entailment graph learning.

Findings

EGT2 significantly outperforms existing methods on benchmark datasets.

Soft transitivity constraints effectively mitigate sparsity issues.

The approach improves the modeling of logical entailment structures.

Abstract

Typed entailment graphs try to learn the entailment relations between predicates from text and model them as edges between predicate nodes. The construction of entailment graphs usually suffers from severe sparsity and unreliability of distributional similarity. We propose a two-stage method, Entailment Graph with Textual Entailment and Transitivity (EGT2). EGT2 learns local entailment relations by recognizing possible textual entailment between template sentences formed by typed CCG-parsed predicates. Based on the generated local graph, EGT2 then uses three novel soft transitivity constraints to consider the logical transitivity in entailment structures. Experiments on benchmark datasets show that EGT2 can well model the transitivity in entailment graph to alleviate the sparsity issue, and lead to significant improvement over current state-of-the-art methods.