Lexicosyntactic Inference in Neural Models

2018/08/19 by Aaron Steven White, Rachel Rudinger, White, Aaron Steven +5 · 1 citation
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques #Text Readability and Simplification #Topic Modeling

paper · pdf · doi:10.48550/arxiv.1808.06232

openalex publication_date 2018/08/19 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Citations

• Learning to Execute
• Long Short-Term Memory
• Fine-grained Analysis of Sentence Embeddings Using Auxiliary Prediction Tasks
• SentEval: An Evaluation Toolkit for Universal Sentence Representations
• A large annotated corpus for learning natural language inference

Cited by

• LeWiDi-2025 at NLPerspectives: The Third Edition of the Learning with Disagreements Shared Task

Related

• Neural models of factuality
• Graph based Neural Networks for Event Factuality Prediction using Syntactic and Semantic Structures
• Neural Language Models as Psycholinguistic Subjects: Representations of\n Syntactic State
• When Does Syntax Mediate Neural Language Model Performance? Evidence from Dropout Probes
• Intensional Gaps: Relating veridicality, factivity, doxasticity, bouleticity, and neg-raising