Entailment Graph Learning with Textual Entailment and Soft Transitivity
This work addresses a domain-specific problem in natural language processing for researchers and practitioners dealing with entailment graphs, offering incremental advancements through novel constraints.
The paper tackled the sparsity and unreliability issues in constructing typed entailment graphs by proposing a two-stage method that learns local entailment relations from textual templates and applies soft transitivity constraints, resulting in significant improvements over state-of-the-art methods on benchmark datasets.
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.