Multi-Review Fusion-in-Context

Aviv Slobodkin, Ori Shapira, Ran Levy, Ido Dagan

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Grounded text generation, encompassing tasks such as long-form question-answering and summarization, necessitates both content selection and content consolidation. Current end-to-end methods are difficult to control and interpret due to their opaqueness. Accordingly, recent works have proposed a modular approach, with separate components for each step. Specifically, we focus on the second subtask, of generating coherent text given pre-selected content in a multi-document setting. Concretely, we formalize Fusion-in-Context (FiC) as a standalone task, whose input consists of source texts with highlighted spans of targeted content. A model then needs to generate a coherent passage that includes all and only the target information. Our work includes the development of a curated dataset of 1000 instances in the reviews domain, alongside a novel evaluation framework for assessing the faithfulness and coverage of highlights, which strongly correlate to human judgment. Several baseline models exhibit promising outcomes and provide insightful analyses. This study lays the groundwork for further exploration of modular text generation in the multi-document setting, offering potential improvements in the quality and reliability of generated content.

Original languageEnglish
Title of host publicationFindings of the Association for Computational Linguistics
Subtitle of host publicationNAACL 2024 - Findings
EditorsKevin Duh, Helena Gomez, Steven Bethard
PublisherAssociation for Computational Linguistics (ACL)
Pages3003-3021
Number of pages19
ISBN (Electronic)9798891761193
DOIs
StatePublished - 2024
Event2024 Findings of the Association for Computational Linguistics: NAACL 2024 - Mexico City, Mexico
Duration: 16 Jun 202421 Jun 2024

Publication series

NameFindings of the Association for Computational Linguistics: NAACL 2024 - Findings

Conference

Conference2024 Findings of the Association for Computational Linguistics: NAACL 2024
Country/TerritoryMexico
CityMexico City
Period16/06/2421/06/24

All Science Journal Classification (ASJC) codes

  • Computational Theory and Mathematics
  • Software

Cite this