Learning to Ignore: Long Document Coreference with Bounded Memory Neural Networks
Learning to Ignore: Long Document Coreference with Bounded Memory Neural Networks
复制标题
DOI：
10.18653/v1/2020.emnlp-main.685
复制
发表时间：
2020-10
期刊：
影响因子：
--
通讯作者：
Shubham Toshniwal;Sam Wiseman;Allyson Ettinger;Karen Livescu;Kevin Gimpel
中科院分区：
文献类型：
--
作者：
Shubham Toshniwal;Sam Wiseman;Allyson Ettinger;Karen Livescu;Kevin Gimpel
由于当前模型的大内存和运行时需求，长文档共同引用解析仍然是一项具有挑战性的任务。最近仅使用实体的全局表示进行增量共同引用解析的工作显示了实际的好处，但需要将所有实体保存在内存中，这对于长文档来说是不切实际的。我们认为将所有实体保存在内存中是不必要的，我们提出了一个内存增强神经网络，它一次只跟踪有限数量的实体，从而保证文档长度的线性运行时间。我们表明(a)该模型与OntoNotes和LitBank上具有高内存和计算需求的模型仍然具有竞争力，并且(b)该模型学习了一种有效的内存管理策略，轻松优于基于规则的策略。
Long document coreference resolution remains a challenging task due to the large memory and runtime requirements of current models. Recent work doing incremental coreference resolution using just the global representation of entities shows practical benefits but requires keeping all entities in memory, which can be impractical for long documents. We argue that keeping all entities in memory is unnecessary, and we propose a memory-augmented neural network that tracks only a small bounded number of entities at a time, thus guaranteeing a linear runtime in length of document. We show that (a) the model remains competitive with models with high memory and computational requirements on OntoNotes and LitBank, and (b) the model learns an efficient memory management strategy easily outperforming a rule-based strategy.