Lexicosyntactic Inference in Neural Models


May 23, 2018 OpenReview Anonymous Preprint Blind Submission readers: everyone Show Bibtex
  • 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 predicates 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: semantics, clause-embedding, lexicosyntactic, inference, neural, lstm, rnn
0 Replies