PRIDE: Predicting Relationships in Conversations
Anna Tigunova, Paramita Mirza, Andrew Yates, Gerhard Weikum
Abstract
Automatically extracting interpersonal relationships of conversation interlocutors can enrich personal knowledge bases to enhance personalized search, recommenders and chatbots. To infer speakers’ relationships from dialogues we propose PRIDE, a neural multi-label classifier, based on BERT and Transformer for creating a conversation representation. PRIDE utilizes dialogue structure and augments it with external knowledge about speaker features and conversation style. Unlike prior works, we address multi-label prediction of fine-grained relationships. We release large-scale datasets, based on screenplays of movies and TV shows, with directed relationships of conversation participants. Extensive experiments on both datasets show superior performance of PRIDE compared to the state-of-the-art baselines.
BibTeX
@inproceedings{tigunova-etal-2021-pride,
title = "{PRIDE}: {P}redicting {R}elationships in {C}onversations",
author = "Tigunova, Anna and
Mirza, Paramita and
Yates, Andrew and
Weikum, Gerhard",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2021",
address = "Online and Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.emnlp-main.380/",
doi = "10.18653/v1/2021.emnlp-main.380",
pages = "4636--4650"
}