arXiv Open Access 2023

Situated Natural Language Explanations

Zining Zhu Haoming Jiang Jingfeng Yang Sreyashi Nag Chao Zhang +4 lainnya

Lihat Sumber

Abstrak

Natural language is among the most accessible tools for explaining decisions to humans, and large pretrained language models (PLMs) have demonstrated impressive abilities to generate coherent natural language explanations (NLE). The existing NLE research perspectives do not take the audience into account. An NLE can have high textual quality, but it might not accommodate audiences' needs and preference. To address this limitation, we propose an alternative perspective, \textit{situated} NLE. On the evaluation side, we set up automated evaluation scores. These scores describe the properties of NLEs in lexical, semantic, and pragmatic categories. On the generation side, we identify three prompt engineering techniques and assess their applicability on the situations. Situated NLE provides a perspective and facilitates further research on the generation and evaluation of explanations.

Topik & Kata Kunci

cs.CL

Penulis (9)

Zining Zhu

Haoming Jiang

Jingfeng Yang

Sreyashi Nag

Chao Zhang

Jie Huang

Yifan Gao

Frank Rudzicz

Bing Yin

Format Sitasi

APA MLA BibTeX

Zhu, Z., Jiang, H., Yang, J., Nag, S., Zhang, C., Huang, J. et al. (2023). Situated Natural Language Explanations. https://arxiv.org/abs/2308.14115

Akses Cepat

Lihat di Sumber

Informasi Jurnal

Tahun Terbit: 2023
Bahasa: en
Sumber Database: arXiv
Akses: Open Access ✓