Adapting Coreference Resolution to Twitter Conversations
| Autor: | Annalena Kohnert, Veronika Solopova, Manfred Stede, Berfin Aktaş |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Coreference
Computer science business.industry media_common.quotation_subject 02 engineering and technology Deixis computer.software_genre 03 medical and health sciences 0302 clinical medicine 030221 ophthalmology & optometry 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Conversation Artificial intelligence business computer Natural language processing media_common |
| Zdroj: | EMNLP (Findings) |
| DOI: | 10.18653/v1/2020.findings-emnlp.222 |
| Popis: | 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%. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|