Anaphora Resolution in Dialogue: System Description (CODI-CRAC 2022 Shared Task)
원문 초록
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.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Deep sparse multi-task learning for feature selection in Alzheimer’s disease diagnosis
Tri-Learn Graph Fusion Network for Attributed Graph Clustering
Robust-Multi-Task Gradient Boosting
Car Object Counting and Position Estimation via Extension of the CLIP-EBC Framework
SAMO: A Lightweight Sharpness-Aware Approach for Multi-Task Optimization with Joint Global-Local Perturbation
HERCULES: Hierarchical Embedding-based Recursive Clustering Using LLMs for Efficient Summarization
토론
이 논문과 연결된 포럼 글이 아직 없습니다.