A Unified Approach to Entity-Centric Context Tracking in Social Conversations

Ulrich Rückert, Srinivas Sunkara, Abhinav Rastogi, Sushant Prakash, Pranav Khaitan


Abstract
In human-human conversations, Context Tracking deals with identifying important entities and keeping track of their properties and relationships. This is a challenging problem that encompasses several subtasks such as slot tagging, coreference resolution, resolving plural mentions and entity linking. We approach this problem as an end-to-end modeling task where the conversational context is represented by an entity repository containing the entity references mentioned so far, their properties and the relationships between them. The repository is updated turn-by-turn, thus making training and inference computationally efficient even for long conversations. This paper lays the groundwork for an investigation of this framework in two ways. First, we release Contrack, a large scale human-human conversation corpus for context tracking with people and location annotations. It contains over 7000 conversations with an average of 11.8 turns, 5.8 entities and 15.2 references per conversation. Second, we open-source a neural network architecture for context tracking. Finally we compare this network to state-of-the-art approaches for the subtasks it subsumes and report results on the involved tradeoffs.
Anthology ID:
2022.lrec-1.136
Volume:
Proceedings of the Thirteenth Language Resources and Evaluation Conference
Month:
June
Year:
2022
Address:
Marseille, France
Editors:
Nicoletta Calzolari, Frédéric Béchet, Philippe Blache, Khalid Choukri, Christopher Cieri, Thierry Declerck, Sara Goggi, Hitoshi Isahara, Bente Maegaard, Joseph Mariani, Hélène Mazo, Jan Odijk, Stelios Piperidis
Venue:
LREC
SIG:
Publisher:
European Language Resources Association
Note:
Pages:
1275–1285
Language:
URL:
https://aclanthology.org/2022.lrec-1.136
DOI:
Bibkey:
Cite (ACL):
Ulrich Rückert, Srinivas Sunkara, Abhinav Rastogi, Sushant Prakash, and Pranav Khaitan. 2022. A Unified Approach to Entity-Centric Context Tracking in Social Conversations. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 1275–1285, Marseille, France. European Language Resources Association.
Cite (Informal):
A Unified Approach to Entity-Centric Context Tracking in Social Conversations (Rückert et al., LREC 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.lrec-1.136.pdf
Code
 google-research-datasets/contrack