End-to-end Neural Coreference Resolution
Kenton Lee Luheng He Mike Lewis Luke Zettlemoyer
Abstract
We introduce the first end-to-end coreference resolution model and show that it significantly outperforms all previous work without using a syntactic parser or hand-engineered mention detector. The key idea is to directly consider all spans in a document as potential mentions and learn distributions over possible antecedents for each. The model computes span embeddings that combine context-dependent boundary representations with a head-finding attention mechanism. It is trained to maximize the marginal likelihood of gold antecedent spans from coreference clusters and is factored to enable aggressive pruning of potential mentions. Experiments demonstrate state-of-the-art performance, with a gain of 1.5 F1 on the OntoNotes benchmark and by 3.1 F1 using a 5-model ensemble, despite the fact that this is the first approach to be successfully trained with no external resources.
中文速览
指代消解（coreference resolution）任务要把文中指向同一实体的所有表述自动归为一组，过去最好的系统都依赖句法分析器和人工设计的候选提及检测器，流程复杂且错误会逐级传播。这项工作提出了第一个真正端到端的神经网络模型：直接把文档中所有可能的文本片段（span）当作候选提及，用双向LSTM结合注意力机制学出每个片段的向量表示，再对所有片段对打分、预测先行词，整个过程无需外部句法工具。为了应对计算量随文档长度四次方增长的挑战，模型用单元提及得分对候选片段做激进剪枝，同时通过最大化正确先行词的边际似然来联合训练提及检测与共指预测。实验在CoNLL-2012英语基准测试上比此前最优系统高出1.5 F1分（集成模型高出3.1 F1），证明去掉外部资源不仅没有损失，反而能做得更好，为后续大规模端到端共指解析奠定了重要基础。
原文 arXiv:1707.07045;中英对照 + 大白话阅读 https://aha.fim.ai/paper/1707.07045v2