hinoki at SemEval-2024 Task 7: Numeral-Aware Headline Generation (English)

Hinoki Crum, Steven Bethard

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Scopus citations

Abstract

Numerical reasoning is challenging even for large pre-trained language models. We show that while T5 models are capable of generating relevant headlines with proper numerical values, they can also make mistakes in reading comprehension and miscalculate numerical values. To overcome these issues, we propose a two-step training process: first train models to read text and generate formal representations of calculations, then train models to read calculations and generate numerical values. On the SemEval 2024 Task 7 headline fill-in-the-blank task, our two-stage Flan-T5-based approach achieved 88% accuracy. On the headline generation task, our T5-based approach achieved RougeL of 0.390, BERT F1 Score of 0.453, and MoverScore of 0.587.

Original languageEnglish (US)
Title of host publicationSemEval 2024 - 18th International Workshop on Semantic Evaluation, Proceedings of the Workshop
EditorsAtul Kr. Ojha, A. Seza Dohruoz, Harish Tayyar Madabushi, Giovanni Da San Martino, Sara Rosenthal, Aiala Rosa
PublisherAssociation for Computational Linguistics (ACL)
Pages34-39
Number of pages6
ISBN (Electronic)9798891761070
StatePublished - 2024
Event18th International Workshop on Semantic Evaluation, SemEval 2024, co-located with the 2024 Annual Conference of the North American Chapter of the Association for Computational Linguistics, NAACL 2024 - Hybrid, Mexico City, Mexico
Duration: Jun 20 2024Jun 21 2024

Publication series

NameSemEval 2024 - 18th International Workshop on Semantic Evaluation, Proceedings of the Workshop

Conference

Conference18th International Workshop on Semantic Evaluation, SemEval 2024, co-located with the 2024 Annual Conference of the North American Chapter of the Association for Computational Linguistics, NAACL 2024
Country/TerritoryMexico
CityHybrid, Mexico City
Period6/20/246/21/24

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Computer Science Applications
  • Theoretical Computer Science

Fingerprint

Dive into the research topics of 'hinoki at SemEval-2024 Task 7: Numeral-Aware Headline Generation (English)'. Together they form a unique fingerprint.

Cite this