Speaker Information Can Guide Models to Better Inductive Biases: A Case Study On Predicting Code-Switching

Alissa Ostapenko, Shuly Wintner, Melinda Fricke, Yulia Tsvetkov

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

Abstract

Natural language processing (NLP) models trained on people-generated data can be unreliable because, without any constraints, they can learn from spurious correlations that are not relevant to the task. We hypothesize that enriching models with speaker information in a controlled, educated way can guide them to pick up on relevant inductive biases. For the speaker-driven task of predicting code-switching points in English-Spanish bilingual dialogues, we show that adding sociolinguistically-grounded speaker features as prepended prompts significantly improves accuracy. We find that by adding influential phrases to the input, speaker-informed models learn useful and explainable linguistic information. To our knowledge, we are the first to incorporate speaker characteristics in a neural model for code-switching, and more generally, take a step towards developing transparent, personalized models that use speaker information in a controlled way.

Original languageEnglish
Title of host publicationACL 2022 - 60th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)
EditorsSmaranda Muresan, Preslav Nakov, Aline Villavicencio
PublisherAssociation for Computational Linguistics (ACL)
Pages3853-3867
Number of pages15
ISBN (Electronic)9781955917216
StatePublished - 2022
Event60th Annual Meeting of the Association for Computational Linguistics, ACL 2022 - Dublin, Ireland
Duration: 22 May 202227 May 2022

Publication series

NameProceedings of the Annual Meeting of the Association for Computational Linguistics
Volume1
ISSN (Print)0736-587X

Conference

Conference60th Annual Meeting of the Association for Computational Linguistics, ACL 2022
Country/TerritoryIreland
CityDublin
Period22/05/2227/05/22

Bibliographical note

Publisher Copyright:
© 2022 Association for Computational Linguistics.

ASJC Scopus subject areas

  • Computer Science Applications
  • Linguistics and Language
  • Language and Linguistics

Fingerprint

Dive into the research topics of 'Speaker Information Can Guide Models to Better Inductive Biases: A Case Study On Predicting Code-Switching'. Together they form a unique fingerprint.

Cite this