Paper introduces multi-granularity reasoning for NLI

Arxiv CS.CL (NLP/language models)

The paper proposes a multi-granularity reasoning approach for Natural Language Inference (NLI), determining logical relationships between premise and hypothesis. It builds on transformer-based pre-trained models.

Arxiv CS.CL (NLP/language models)·Chunling XiDi Liang

6 days ago