Measuring Attribution in Natural Language Generation Models

With recent improvements in natural language generation (NLG) models for various applications, it has become imperative to have the means to identify and evaluate whether NLG output is only sharing verifiable information about the external world. In this work, we present a new evaluation framework e...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2022-08
Main Authors: Rashkin, Hannah, Nikolaev, Vitaly, Lamm, Matthew, Aroyo, Lora, Collins, Michael, Das, Dipanjan, Petrov, Slav, Gaurav Singh Tomar, Turc, Iulia, Reitter, David
Format: Article
Language:English
Subjects:
Annotations
Evaluation
Guidelines
Natural language
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:With recent improvements in natural language generation (NLG) models for various applications, it has become imperative to have the means to identify and evaluate whether NLG output is only sharing verifiable information about the external world. In this work, we present a new evaluation framework entitled Attributable to Identified Sources (AIS) for assessing the output of natural language generation models, when such output pertains to the external world. We first define AIS and introduce a two-stage annotation pipeline for allowing annotators to appropriately evaluate model output according to AIS guidelines. We empirically validate this approach on generation datasets spanning three tasks (two conversational QA datasets, a summarization dataset, and a table-to-text dataset) via human evaluation studies that suggest that AIS could serve as a common framework for measuring whether model-generated statements are supported by underlying sources. We release guidelines for the human evaluation studies.
ISSN:2331-8422