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.- Anthology ID:
- 2021.emnlp-main.380
- Volume:
- Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
- Month:
- November
- Year:
- 2021
- Address:
- Online and Punta Cana, Dominican Republic
- Editors:
- Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 4636–4650
- Language:
- URL:
- https://aclanthology.org/2021.emnlp-main.380
- DOI:
- 10.18653/v1/2021.emnlp-main.380
- Cite (ACL):
- Anna Tigunova, Paramita Mirza, Andrew Yates, and Gerhard Weikum. 2021. PRIDE: Predicting Relationships in Conversations. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 4636–4650, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
- Cite (Informal):
- PRIDE: Predicting Relationships in Conversations (Tigunova et al., EMNLP 2021)
- PDF:
- https://preview.aclanthology.org/ingest-bitext-workshop/2021.emnlp-main.380.pdf
- Data
- DDRel