Blindness to Modality Helps Entailment Graph Mining
This is an incremental finding for natural language processing researchers working on entailment graphs and related downstream applications.
The study tackled the problem of improving entailment graph learning by examining the role of modality, and found that stripping modal modifiers from predicates increased performance, suggesting that ignoring modality can be beneficial for this task.
Understanding linguistic modality is widely seen as important for downstream tasks such as Question Answering and Knowledge Graph Population. Entailment Graph learning might also be expected to benefit from attention to modality. We build Entailment Graphs using a news corpus filtered with a modality parser, and show that stripping modal modifiers from predicates in fact increases performance. This suggests that for some tasks, the pragmatics of modal modification of predicates allows them to contribute as evidence of entailment.