On the Diversity and Limits of Human Explanations

06/22/2021
by   Chenhao Tan, et al.
0

A growing effort in NLP aims to build datasets of human explanations. However, the term explanation encompasses a broad range of notions, each with different properties and ramifications. Our goal is to provide an overview of diverse types of explanations and human limitations, and discuss implications for collecting and using explanations in NLP. Inspired by prior work in psychology and cognitive sciences, we group existing human explanations in NLP into three categories: proximal mechanism, evidence, and procedure. These three types differ in nature and have implications for the resultant explanations. For instance, procedure is not considered explanations in psychology and connects with a rich body of work on learning from instructions. The diversity of explanations is further evidenced by proxy questions that are needed for annotators to interpret and answer open-ended why questions. Finally, explanations may require different, often deeper, understandings than predictions, which casts doubt on whether humans can provide useful explanations in some tasks.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/29/2019

Weight of Evidence as a Basis for Human-Oriented Explanations

Interpretability is an elusive but highly sought-after characteristic of...
research
04/19/2022

A survey on improving NLP models with human explanations

Training a model with access to human explanations can improve data effi...
research
06/12/2020

Generalized SHAP: Generating multiple types of explanations in machine learning

Many important questions about a model cannot be answered just explainin...
research
12/30/2020

Human Evaluation of Spoken vs. Visual Explanations for Open-Domain QA

While research on explaining predictions of open-domain QA systems (ODQA...
research
02/24/2021

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

Explainable NLP (ExNLP) has increasingly focused on collecting human-ann...
research
04/27/2021

A Human-Centered Interpretability Framework Based on Weight of Evidence

In this paper, we take a human-centered approach to interpretable machin...
research
05/08/2021

On Guaranteed Optimal Robust Explanations for NLP Models

We build on abduction-based explanations for ma-chine learning and devel...

Please sign up or login with your details

Forgot password? Click here to reset