Teach Me to Explain: A Review of Datasets for Explainable NLP

02/24/2021
by   Sarah Wiegreffe, et al.
0

Explainable NLP (ExNLP) has increasingly focused on collecting human-annotated explanations. These explanations are used downstream in three ways: as data augmentation to improve performance on a predictive task, as a loss signal to train models to produce explanations for their predictions, and as a means to evaluate the quality of model-generated explanations. In this review, we identify three predominant classes of explanations (highlights, free-text, and structured), organize the literature on annotating each type, point to what has been learned to date, and give recommendations for collecting ExNLP datasets in the future.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 4

07/12/2017

Explainable Entity-based Recommendations with Knowledge Graphs

Explainable recommendation is an important task. Many methods have been ...
10/01/2020

A Survey of the State of Explainable AI for Natural Language Processing

Recent years have seen important advances in the quality of state-of-the...
06/22/2021

On the Diversity and Limits of Human Explanations

A growing effort in NLP aims to build datasets of human explanations. Ho...
11/01/2018

Towards Explainable NLP: A Generative Explanation Framework for Text Classification

Building explainable systems is a critical problem in the field of Natur...
05/05/2021

Do Natural Language Explanations Represent Valid Logical Arguments? Verifying Entailment in Explainable NLI Gold Standards

An emerging line of research in Explainable NLP is the creation of datas...
09/09/2021

SPECTRA: Sparse Structured Text Rationalization

Selective rationalization aims to produce decisions along with rationale...
11/16/2021

Few-Shot Self-Rationalization with Natural Language Prompts

Self-rationalization models that predict task labels and generate free-t...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.