Resolving Indirect Referring Expressions for Entity Selection

Mohammad Javad Hosseini, Filip Radlinski, Silvia Pareti, Annie Louis


Abstract
Recent advances in language modeling have enabled new conversational systems. In particular, it is often desirable for people to make choices among specified options when using such systems. We address the problem of reference resolution, when people use natural expressions to choose between real world entities. For example, given the choice ‘Should we make a Simnel cake or a Pandan cake¿ a natural response from a non-expert may be indirect: ‘let’s make the green one‘. Reference resolution has been little studied with natural expressions, thus robustly understanding such language has large potential for improving naturalness in dialog, recommendation, and search systems. We create AltEntities (Alternative Entities), a new public dataset of entity pairs and utterances, and develop models for the disambiguation problem. Consisting of 42K indirect referring expressions across three domains, it enables for the first time the study of how large language models can be adapted to this task. We find they achieve 82%-87% accuracy in realistic settings, which while reasonable also invites further advances.
Anthology ID:
2023.acl-long.688
Volume:
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
12313–12335
Language:
URL:
https://aclanthology.org/2023.acl-long.688
DOI:
10.18653/v1/2023.acl-long.688
Award:
 Area Chair Award (Discourse and Pragmatics)
Bibkey:
Cite (ACL):
Mohammad Javad Hosseini, Filip Radlinski, Silvia Pareti, and Annie Louis. 2023. Resolving Indirect Referring Expressions for Entity Selection. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 12313–12335, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Resolving Indirect Referring Expressions for Entity Selection (Hosseini et al., ACL 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.acl-long.688.pdf
Video:
 https://aclanthology.org/2023.acl-long.688.mp4