论文标题
佩特拉：一个稀疏监督的人追踪的记忆模型
PeTra: A Sparsely Supervised Memory Model for People Tracking
论文作者
论文摘要
我们提出了佩特拉（Petra），这是一个由内存的神经网络，旨在跟踪其内存插槽中的实体。使用GAP代词分辨率数据集中的稀疏注释对PETRA进行了训练，并在使用更简单的体系结构的同时，在任务上胜过任务的先验内存模型。我们从经验上比较了关键建模选择，发现我们可以简化内存模块设计的几个方面，同时保持强劲的性能。为了衡量跟踪记忆模型的能力的人，我们（a）提出了基于计算文本中独特实体数量的新诊断评估，以及（b）进行小规模的人类评估，以比较人们相对于先前方法的PETRA记忆日志中人们跟踪的证据。佩特拉（Petra）在两种评估中都非常有效，表明了其在注释有限的训练中，可以追踪人们在记忆中的能力。
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.
