Reinforced Multiple Instance Selection for Speaker Attribute Prediction

Alireza Salkhordeh Ziabari, Ali Omrani, Parsa Hejabi, Preni Golazizian, Brendan Kennedy, Payam Piray, Morteza Dehghani


Abstract
Language usage is related to speaker age, gender, moral concerns, political ideology, and other attributes. Current state-of-the-art methods for predicting these attributes take a speaker’s utterances as input and provide a prediction per speaker attribute. Most of these approaches struggle to handle a large number of utterances per speaker. This difficulty is primarily due to the computational constraints of the models. Additionally, only a subset of speaker utterances may be relevant to specific attributes. In this paper, we formulate speaker attribute prediction as a Multiple Instance Learning (MIL) problem and propose RL-MIL, a novel approach based on Reinforcement Learning (RL) that effectively addresses both of these challenges. Our experiments demonstrate that our RL-based methodology consistently outperforms previous approaches across a range of related tasks: predicting speakers’ psychographics and demographics from social media posts, and political ideologies from transcribed speeches. We create synthetic datasets and investigate the behavior of RL-MIL systematically. Our results show the success of RL-MIL in improving speaker attribute prediction by learning to select relevant speaker utterances.
Anthology ID:
2024.naacl-long.181
Volume:
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Kevin Duh, Helena Gomez, Steven Bethard
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3307–3321
Language:
URL:
https://aclanthology.org/2024.naacl-long.181
DOI:
Bibkey:
Cite (ACL):
Alireza Salkhordeh Ziabari, Ali Omrani, Parsa Hejabi, Preni Golazizian, Brendan Kennedy, Payam Piray, and Morteza Dehghani. 2024. Reinforced Multiple Instance Selection for Speaker Attribute Prediction. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 3307–3321, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
Reinforced Multiple Instance Selection for Speaker Attribute Prediction (Salkhordeh Ziabari et al., NAACL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.naacl-long.181.pdf
Copyright:
 2024.naacl-long.181.copyright.pdf