论文标题
学会忽略：长期文档核心与有限记忆神经网络
Learning to Ignore: Long Document Coreference with Bounded Memory Neural Networks
论文作者
论文摘要
由于当前模型的庞大内存和运行时要求，长期文档核心分辨率仍然是一项具有挑战性的任务。最近仅使用实体的全球表示进行增量核心解决方案的工作显示出实际的好处，但要求将所有实体保持在内存中，这对于长文档而言可能是不切实际的。我们认为，将所有实体保持在内存不必要，并且我们提出了一个由内存的神经网络，该网络一次仅跟踪一个少量的实体，从而保证文档长度的线性运行时。我们表明（a）模型与具有高内存和计算要求的模型保持竞争力，并且（b）该模型学习了一种有效的内存管理策略，可以轻松地胜过基于规则的策略。
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.
