Situated Natural Language Explanations

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhu, Zining, Jiang, Haoming, Yang, Jingfeng, Nag, Sreyashi, Zhang, Chao, Huang, Jie, Gao, Yifan, Rudzicz, Frank, Yin, Bing
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909148538470400
author Zhu, Zining
Jiang, Haoming
Yang, Jingfeng
Nag, Sreyashi
Zhang, Chao
Huang, Jie
Gao, Yifan
Rudzicz, Frank
Yin, Bing
author_facet Zhu, Zining
Jiang, Haoming
Yang, Jingfeng
Nag, Sreyashi
Zhang, Chao
Huang, Jie
Gao, Yifan
Rudzicz, Frank
Yin, Bing
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2308_14115
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Situated Natural Language Explanations
Zhu, Zining
Jiang, Haoming
Yang, Jingfeng
Nag, Sreyashi
Zhang, Chao
Huang, Jie
Gao, Yifan
Rudzicz, Frank
Yin, Bing
Computation and Language
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.
title Situated Natural Language Explanations
topic Computation and Language
url https://arxiv.org/abs/2308.14115