Understanding by Understanding Not: Modeling Negation in Language Models

2021/05/07 by Arian Hosseini, Hosseini, Arian, Siva Reddy +9 · 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.2105.03519

openalex publication_date 2021/05/07 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Negation is a core construction in natural language. Despite being very successful on many tasks, state-of-the-art pre-trained language models often handle negation incorrectly. To improve language models in this regard, we propose to augment the language modeling objective with an unlikelihood objective that is based on negated generic sentences from a raw text corpus. By training BERT with the resulting combined objective we reduce the mean top~1 error rate to 4% on the negated LAMA dataset. We also see some improvements on the negated NLI benchmarks.

Cited by

• A Comprehensive Taxonomy of Negation for NLP and Neural Retrievers

Related

• This is not a Dataset: A Large Negation Benchmark to Challenge Large Language Models
• Language models are not naysayers: An analysis of language models on negation benchmarks
• Making Language Models Robust Against Negation
• This is not correct! Negation-aware Evaluation of Language Generation Systems
• Learning Robust Negation Text Representations