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.
@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}
}