natural-language-processing

Explanation Generation

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in explanation-generation

Trend

Dataset

Best Model

Actions

WHOOPS! A Vision-and-Language Benchmark of Synthetic and Compositional Images

CLEVR-X

Libraries

i

Use these libraries to find explanation-generation models and implementations

csinva/imodelsX

2 papers 74

Datasets

VCR

Subtasks

No subtasks available.

Most implemented papers

Explainable Automated Fact-Checking for Public Health Claims

Neema Kotonya, Francesca Toni•Sun Oct 18 2020

The results indicate that, by training on in-domain data, gains can be made in explainable, automated fact-checking for claims which require specific expertise.

320

Content

VQA-X

e-SNLI-VE

VCR

E-ReDial

SpanEX

0

Paper Graph

AR-BERT: Aspect-relation enhanced Aspect-level Sentiment Classification with Multi-modal Explanations

Sekh Mainul Islam, Sourangshu Bhattacharya•Wed Aug 25 2021

AR-BERT is proposed, a novel two-level global-local entity embedding scheme that allows efficient joint training of KG-based aspect embeddings and ALSC models and introduces the problem of determining mode significance in multi-modal explanation generation, and proposes a two step solution.

12 0

Paper Graph

Red Dragon AI at TextGraphs 2019 Shared Task: Language Model Assisted Explanation Generation

Yew Ken Chia, Sam Witteveen, Martin Andrews•Tue Nov 19 2019

The TextGraphs-13 Shared Task on Explanation Regeneration asked participants to develop methods to reconstruct gold explanations for elementary science questions, and Red Dragon AI’s entries used the language of the questions and explanation text directly, rather than a constructing a separate graph-like representation.

17 0

Paper Graph

Explaining Patterns in Data with Language Models via Interpretable Autoprompting

Jianfeng Gao, Alexander M. Rush, J. Aneja, John X. Morris, Chandan Singh•Fri Dec 31 2021

This work introduces interpretable autoprompting (iPrompt), an algorithm that generates a natural-language string explaining the data that iteratively alternates between generating explanations with an LLM and reranking them based on their performance when used as a prompt.

51 0

Paper Graph

QED: A Framework and Dataset for Explanations in Question Answering

Chris Alberti, Eunsol Choi, J. Palomaki, Michael Collins, Matthew Lamm, D. Andor, Livio Baldini Soares•Mon Sep 07 2020

A large user study is described showing that the presence of QED explanations significantly improves the ability of untrained raters to spot errors made by a strong neural QA baseline.

80 0

Paper Graph

TE2Rules: Explaining Tree Ensembles using Rules

G. R. Lal, Xiaotong Chen, Varun Mithal•Tue Jun 28 2022

TE2Rules (Tree Ensemble to Rules), a novel approach for explaining binary classification tree ensemble models through a list of rules, particularly focusing on explaining the minority class, is introduced.

4 0

Paper Graph

Towards Interpretable Natural Language Understanding with Explanations as Latent Variables

Hanlin Zhang, Maosong Sun, Xiaodan Liang, Wangchunshu Zhou, Chenyan Xiong, Jian Tang, Jinyi Hu•Fri Oct 23 2020

This paper develops a general framework for interpretable natural language understanding that requires only a small set of human annotated explanations for training and proposes an explanation-based self-training method under this framework for semi-supervised learning.

47 0

Paper Graph

Leakage-Adjusted Simulatability: Can Models Generate Non-Trivial Explanations of Their Behavior in Natural Language?

Mohit Bansal, Shiyue Zhang, Peter Hase, Harry Xie•Wed Oct 07 2020

A leakage-adjusted simulatability (LAS) metric is introduced for evaluating NL explanations, which measures how well explanations help an observer predict a model’s output, while controlling for how explanations can directly leak the output.

112 0

Paper Graph

Explaining black box text modules in natural language with language models

Jianfeng Gao, Chandan Singh, Shailee Jain, Aliyah R. Hsu, Richard J. Antonello, Alexander G. Huth, Bin Yu•Tue May 16 2023

This work introduces Summarize and Score (SASC), a method that takes in a text module and returns a natural language explanation of the module's selectivity along with a score for how reliable the explanation is, and shows that SASC can generate explanations for the response of individual fMRI voxels to language stimuli.

66 0

Paper Graph

Elaborative Simplification: Content Addition and Explanation Generation in Text Simplification

Junyi Jessy Li, Neha Srikanth•Mon Oct 19 2020

This work introduces a new annotated dataset of 1.3K instances of elaborative simplification and analyzes how entities, ideas, and concepts are elaborated through the lens of contextual specificity, and establishes baselines for elaboration generation using large scale pre-trained language models.

50 0

Paper Graph

Adding a benchmark result helps the community track progress.