English

Lexicosyntactic Inference in Neural Models

Computation and Language 2018-08-21 v1

Abstract

We investigate neural models' ability to capture lexicosyntactic inferences: inferences triggered by the interaction of lexical and syntactic information. We take the task of event factuality prediction as a case study and build a factuality judgment dataset for all English clause-embedding verbs in various syntactic contexts. We use this dataset, which we make publicly available, to probe the behavior of current state-of-the-art neural systems, showing that these systems make certain systematic errors that are clearly visible through the lens of factuality prediction.

Keywords

Cite

@article{arxiv.1808.06232,
  title  = {Lexicosyntactic Inference in Neural Models},
  author = {Aaron Steven White and Rachel Rudinger and Kyle Rawlins and Benjamin Van Durme},
  journal= {arXiv preprint arXiv:1808.06232},
  year   = {2018}
}
R2 v1 2026-06-23T03:37:47.919Z