Papers with speaker-grounded encoding
Online Coreference Resolution for Dialogue Processing: Improving Mention-Linking on Real-Time Conversations (2022.starsem-1)
Copied to clipboard
| Challenge: | Existing models for online decoding on active input are not trained to handle an online decode environment. |
| Approach: | They propose a new direction of coreference resolution for online decoding on actively generated input such as dialogue . they propose to use models that accept utterances and their past context and find mentions upon each dialogue turn . |
| Outcome: | The proposed model outperforms the baseline model by 10% on three datasets: Friends, OntoNotes, and BOLT. |