Improving coreference resolution with automatically predicted prosodic information
This work addresses coreference resolution for spoken language applications, but it is incremental as it builds on prior manual annotation methods.
The paper tackled the problem of coreference resolution in spoken language by using automatically predicted prosodic information, such as pitch accents and phrasing, from acoustic features via a CNN model, and showed that this approach significantly improves performance.
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.