Evaluating Discourse Cohesion in Pre-trained Language Models
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916647007158272 |
|---|---|
| author | He, Jie Long, Wanqiu Xiong, Deyi |
| author_facet | He, Jie Long, Wanqiu Xiong, Deyi |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_06137 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Evaluating Discourse Cohesion in Pre-trained Language Models He, Jie Long, Wanqiu Xiong, Deyi Computation and Language 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. |
| title | Evaluating Discourse Cohesion in Pre-trained Language Models |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2503.06137 |