Contrastive Representation Learning for Cross-Document Coreference Resolution of Events and Entities
This addresses a computational bottleneck in natural language processing for researchers and practitioners, though it is incremental as it builds on existing transformer-based methods.
The paper tackles the computational inefficiency of cross-document coreference resolution for events and entities by using contrastive representation learning, reducing transformer computations from n^2 to n at inference time and achieving state-of-the-art results on key metrics in the ECB+ corpus.
Identifying related entities and events within and across documents is fundamental to natural language understanding. We present an approach to entity and event coreference resolution utilizing contrastive representation learning. Earlier state-of-the-art methods have formulated this problem as a binary classification problem and leveraged large transformers in a cross-encoder architecture to achieve their results. For large collections of documents and corresponding set of $n$ mentions, the necessity of performing $n^{2}$ transformer computations in these earlier approaches can be computationally intensive. We show that it is possible to reduce this burden by applying contrastive learning techniques that only require $n$ transformer computations at inference time. Our method achieves state-of-the-art results on a number of key metrics on the ECB+ corpus and is competitive on others.