PeTra：用于人员跟踪的稀疏有监督记忆模型 （cs.CL）---Donuts_choco

我们建议使用 PeTra，一种记忆增强神经网络，旨在跟踪其记忆插槽中的实体。PeTra 使用来自 GAP 代词解析数据集的稀疏注释进行培训，并在使用更简单的体系结构的任务上优于以前的记忆模型。我们根据经验比较了关键建模选择，发现我们在保持其强大性能的前提下，可以简化记忆模块设计的几个方面。同时。为了测量记忆模型的人员跟踪能力，我们（a） 提出了基于计算文本中唯一实体数量的全新诊断评估，以及 （b） 进行小规模人员评估，以比较 PeTra 记忆日志中与以前方法相比人员跟踪的效果。PeTra 在两种评估方式中都非常有效，展示了其在有限的注释训练下跟踪记忆中人员的性能。

原文标题：PeTra: A Sparsely Supervised Memory Model for People Tracking

原文：We propose PeTra, a memory-augmented neural network designed to track entities in its memory slots. PeTra is trained using sparse annotation from the GAP pronoun resolution dataset and outperforms a prior memory model on the task while using a simpler architecture. We empirically compare key modeling choices, finding that we can simplify several aspects of the design of the memory module while retaining strong performance. To measure the people tracking capability of memory models, we (a) propose a new diagnostic evaluation based on counting the number of unique entities in text, and (b) conduct a small scale human evaluation to compare evidence of people tracking in the memory logs of PeTra relative to a previous approach. PeTra is highly effective in both evaluations, demonstrating its ability to track people in its memory despite being trained with limited annotation.

原文作者：Shubham Toshniwal, Allyson Ettinger, Kevin Gimpel, Karen Livescu

原文地址：http://arxiv.org/abs/2005.02990