Adapting Coreference Resolution to Twitter Conversations

Berfin Aktaş, Veronika Solopova, Annalena Kohnert, Manfred Stede


Abstract
The performance of standard coreference resolution is known to drop significantly on Twitter texts. We improve the performance of the (Lee et al., 2018) system, which is originally trained on OntoNotes, by retraining on manually-annotated Twitter conversation data. Further experiments by combining different portions of OntoNotes with Twitter data show that selecting text genres for the training data can beat the mere maximization of training data amount. In addition, we inspect several phenomena such as the role of deictic pronouns in conversational data, and present additional results for variant settings. Our best configuration improves the performance of the”out of the box” system by 21.6%.
Anthology ID:
2020.findings-emnlp.222
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2020
Month:
November
Year:
2020
Address:
Online
Editors:
Trevor Cohn, Yulan He, Yang Liu
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2454–2460
Language:
URL:
https://aclanthology.org/2020.findings-emnlp.222
DOI:
10.18653/v1/2020.findings-emnlp.222
Bibkey:
Cite (ACL):
Berfin Aktaş, Veronika Solopova, Annalena Kohnert, and Manfred Stede. 2020. Adapting Coreference Resolution to Twitter Conversations. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 2454–2460, Online. Association for Computational Linguistics.
Cite (Informal):
Adapting Coreference Resolution to Twitter Conversations (Aktaş et al., Findings 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl24-info/2020.findings-emnlp.222.pdf
Video:
 https://slideslive.com/38940697
Code
 verosol/e2e-coref-to-twitter
Data
OntoNotes 5.0