Higher-order Coreference Resolution with Coarse-to-fine Inference
We introduce a fully differentiable approximation to higher-order inference for coreference resolution. Our approach uses the antecedent distribution from a span-ranking architecture as an attention mechanism to iteratively refine span representations. This enables the model to softly consider multiple hops in the predicted clusters. To alleviate the computational cost of this iterative process, we introduce a coarse-to-fine approach that incorporates a less accurate but more efficient bilinear factor, enabling more aggressive pruning without hurting accuracy. Compared to the existing state-of-the-art span-ranking approach, our model significantly improves accuracy on the English OntoNotes benchmark, while being far more computationally efficient.
Code (5)
Tasks
Coreference ResolutionSimilar Papers 제목 키워드 기반
Revealing the Myth of Higher-Order Inference in Coreference Resolution
This paper analyzes the impact of higher-order inference (HOI) on the task of coreference resolution. HOI has been adapted by almost all recent coreference resolution models without taking much investigation on its true …
AvgClusteringcoreference-resolutionCoreference Resolution+1Sequential Cross-Document Coreference Resolution
Relating entities and events in text is a key component of natural language understanding. Cross-document coreference resolution, in particular, is important for the growing interest in multi-document analysis tasks. In …
coreference-resolutionCoreference ResolutionCross Document Coreference ResolutionNatural Language UnderstandingEnd-to-end Deep Reinforcement Learning Based Coreference Resolution
Recent neural network models have significantly advanced the task of coreference resolution. However, current neural coreference models are usually trained with heuristic loss functions that are computed over a sequence …
coreference-resolutionCoreference ResolutionDeep Reinforcement Learningreinforcement-learning+2End-to-end Neural Coreference Resolution Revisited: A Simple yet Effective Baseline
Since the first end-to-end neural coreference resolution model was introduced, many extensions to the model have been proposed, ranging from using higher-order inference to directly optimizing evaluation metrics using re…
coreference-resolutionCoreference ResolutionAn End-to-End Approach for Full Bridging Resolution
In this article, we describe our submission to the CODI-CRAC 2021 Shared Task on Anaphora Resolution in Dialogues – Track BR (Gold). We demonstrate the performance of an end-to-end transformer-based higher-order corefere…