Improving coreference resolution with automatically predicted prosodic information

Ina Roesiger, Sabrina Stehwien, Arndt Riester, Ngoc Thang Vu


Abstract
Adding manually annotated prosodic information, specifically pitch accents and phrasing, to the typical text-based feature set for coreference resolution has previously been shown to have a positive effect on German data. Practical applications on spoken language, however, would rely on automatically predicted prosodic information. In this paper we predict pitch accents (and phrase boundaries) using a convolutional neural network (CNN) model from acoustic features extracted from the speech signal. After an assessment of the quality of these automatic prosodic annotations, we show that they also significantly improve coreference resolution.
Anthology ID:
W17-4610
Volume:
Proceedings of the Workshop on Speech-Centric Natural Language Processing
Month:
September
Year:
2017
Address:
Copenhagen, Denmark
Editors:
Nicholas Ruiz, Srinivas Bangalore
Venue:
WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
78–83
Language:
URL:
https://aclanthology.org/W17-4610
DOI:
10.18653/v1/W17-4610
Bibkey:
Cite (ACL):
Ina Roesiger, Sabrina Stehwien, Arndt Riester, and Ngoc Thang Vu. 2017. Improving coreference resolution with automatically predicted prosodic information. In Proceedings of the Workshop on Speech-Centric Natural Language Processing, pages 78–83, Copenhagen, Denmark. Association for Computational Linguistics.
Cite (Informal):
Improving coreference resolution with automatically predicted prosodic information (Roesiger et al., 2017)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-3/W17-4610.pdf