Online Coreference Resolution for Dialogue Processing: Improving Mention-Linking on Real-Time Conversations
This work addresses coreference resolution for dialogue systems, enabling real-time processing of conversations, though it is incremental as it builds on existing mention-linking paradigms.
The paper tackled coreference resolution for real-time dialogue by adapting mention-linking models to process utterances incrementally, resulting in a best model that outperformed the baseline by over 10% on datasets like Friends, OntoNotes, and BOLT.
This paper suggests a direction of coreference resolution for online decoding on actively generated input such as dialogue, where the model accepts an utterance and its past context, then finds mentions in the current utterance as well as their referents, upon each dialogue turn. A baseline and four incremental-updated models adapted from the mention-linking paradigm are proposed for this new setting, which address different aspects including the singletons, speaker-grounded encoding and cross-turn mention contextualization. Our approach is assessed on three datasets: Friends, OntoNotes, and BOLT. Results show that each aspect brings out steady improvement, and our best models outperform the baseline by over 10%, presenting an effective system for this setting. Further analysis highlights the task characteristics, such as the significance of addressing the mention recall.