Evaluating Discourse Cohesion in Pre-trained Language Models
This work addresses the need for better evaluation of discourse cohesion in NLP models, but it is incremental as it focuses on creating a test suite rather than advancing model capabilities.
The authors tackled the problem of evaluating discourse cohesion in pre-trained language models by proposing a test suite that assesses cohesive abilities across multiple phenomena, and they compared different models to analyze results, aiming to draw more attention to this area.
Large pre-trained neural models have achieved remarkable success in natural language process (NLP), inspiring a growing body of research analyzing their ability from different aspects. In this paper, we propose a test suite to evaluate the cohesive ability of pre-trained language models. The test suite contains multiple cohesion phenomena between adjacent and non-adjacent sentences. We try to compare different pre-trained language models on these phenomena and analyze the experimental results,hoping more attention can be given to discourse cohesion in the future.