End-to-end Neural Coreference Resolution Revisited: A Simple yet Effective Baseline

Abstract

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 reinforcement learning. Despite improving the coreference resolution performance by a large margin, these extensions add a lot of extra complexity to the original model. Motivated by this observation and the recent advances in pre-trained Transformer language models, we propose a simple yet effective baseline for coreference resolution. Our model is a simplified version of the original neural coreference resolution model, however, it achieves impressive performance, outperforming all recent extended works on the public English OntoNotes benchmark. Our work provides evidence for the necessity of carefully justifying the complexity of existing or newly proposed models, as introducing a conceptual or practical simplification to an existing model can still yield competitive results.

When to Use Large Language Model: Upper Bound Analysis of BM25 Algorithms in Reading Comprehension Task

“…They conducted classification experiments on this basis, so as to compare and analyze the advantages and disadvantages of various methods. Lai T M et al [8] proposed a baseline for coreference resolution, which provides evidence for the necessity of justifying the complexity of existing or newly proposed models. Huliyah et al [9] compared the benchmark of random forest and naive bayes algorithm to know which modeling process has the best value of accuracy for sentiment classification in texts.…”