Work

Q2: : Evaluating Factual Consistency in Knowledge-Grounded Dialogues via Question Generation and Question Answering

Year: 2021

Type: conference-paper

Abstract: Neural knowledge-grounded generative models for dialogue often produce content that is factually inconsistent with the knowledge they rely on, making them unreliable and limiting their applicability.Inspired by recent work on evaluating factual consistency in abstractive summarization, we propose an automatic evaluation metric for factual consistency in knowledge-grounded dialogue using automatic question generation and question answering.Our metric, denoted Q 2 , compares answer spans using natural language inference (NLI), instead of token-based matching as done in previous work.To foster proper evaluation, we curate a novel dataset of dialogue system outputs for the Wizard-of-Wikipedia dataset, manually annotated for factual consistency.We perform a thorough meta-evaluation of Q 2 against other metrics using this dataset and two others, where it consistently shows higher correlation with human judgements.

Source: Conference on Empirical Methods in Natural Language Processing (EMNLP)

DOI: 10.18653/v1/2021.emnlp-main.619

Authors: Or Honovich, Leshem Choshen, Roee Aharoni, Ella Neeman, Idan Szpektor, Omri Abend

Institutions: Google (United States), Hebrew University of Jerusalem

Language: English

Topic: Speech and dialogue systems

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funder: Hebrew University of Jerusalem

OpenAlex ID: W3153947101