Anaphora Resolution in Dialogue: System Description (CODI-CRAC 2022 Shared Task)
This work addresses anaphora resolution for dialogue systems, presenting incremental improvements in a shared task setting.
The paper tackled anaphora resolution in dialogue by testing combinations of incremental clustering with other coreference models, achieving up to a 10.33% improvement over baseline methods.
We describe three models submitted for the CODI-CRAC 2022 shared task. To perform identity anaphora resolution, we test several combinations of the incremental clustering approach based on the Workspace Coreference System (WCS) with other coreference models. The best result is achieved by adding the ''cluster merging'' version of the coref-hoi model, which brings up to 10.33% improvement 1 over vanilla WCS clustering. Discourse deixis resolution is implemented as multi-task learning: we combine the learning objective of corefhoi with anaphor type classification. We adapt the higher-order resolution model introduced in Joshi et al. (2019) for bridging resolution given gold mentions and anaphors.