Smoothing Entailment Graphs with Language Models
This addresses the issue of missing predicates in symbolic entailment models for natural language inference, improving robustness in tasks like question answering, though it is an incremental advancement.
The paper tackled the sparsity problem in Entailment Graphs (EGs) caused by missing predicates, by introducing an unsupervised smoothing method using a language model to approximate missing premises, which improved recall by 25.1 and 16.3 percentage points on two entailment datasets while maintaining precision and explainability.
The diversity and Zipfian frequency distribution of natural language predicates in corpora leads to sparsity in Entailment Graphs (EGs) built by Open Relation Extraction (ORE). EGs are computationally efficient and explainable models of natural language inference, but as symbolic models, they fail if a novel premise or hypothesis vertex is missing at test-time. We present theory and methodology for overcoming such sparsity in symbolic models. First, we introduce a theory of optimal smoothing of EGs by constructing transitive chains. We then demonstrate an efficient, open-domain, and unsupervised smoothing method using an off-the-shelf Language Model to find approximations of missing premise predicates. This improves recall by 25.1 and 16.3 percentage points on two difficult directional entailment datasets, while raising average precision and maintaining model explainability. Further, in a QA task we show that EG smoothing is most useful for answering questions with lesser supporting text, where missing premise predicates are more costly. Finally, controlled experiments with WordNet confirm our theory and show that hypothesis smoothing is difficult, but possible in principle.