Context-Aware Neural Model for Temporal Information Extraction
Context-Aware Neural Model for Temporal Information Extraction
复制标题
DOI：
10.18653/v1/p18-1049
复制
发表时间：
2018-07
期刊：
影响因子：
--
通讯作者：
Yuanliang Meng;Anna Rumshisky
中科院分区：
文献类型：
--
作者：
Yuanliang Meng;Anna Rumshisky
提出了一种上下文感知的神经网络模型用于时态信息提取。该模型具有统一的事件-事件、事件-时间和时间-时间对体系结构。受神经图灵机（NTM）启发的全局上下文层（GCL）以叙述顺序存储处理后的时间关系，并在相关实体进入时检索它们以供使用。然后在上下文中对关系进行分类。GCL模型具有长期记忆和注意力机制，可以解决LSTM等常规RNN无法识别的不规则长距离依赖关系。它不需要任何新的输入功能，同时优于文献中现有的模型。据我们所知，它也是第一个模型，使用NTM类似的架构来处理信息的全球背景下，在语篇规模的自然文本处理。我们将在未来发布源代码。
We propose a context-aware neural network model for temporal information extraction. This model has a uniform architecture for event-event, event-timex and timex-timex pairs. A Global Context Layer (GCL), inspired by Neural Turing Machine (NTM), stores processed temporal relations in narrative order, and retrieves them for use when relevant entities come in. Relations are then classified in context. The GCL model has long-term memory and attention mechanisms to resolve irregular long-distance dependencies that regular RNNs such as LSTM cannot recognize. It does not require any new input features, while outperforming the existing models in literature. To our knowledge it is also the first model to use NTM-like architecture to process the information from global context in discourse-scale natural text processing. We are going to release the source code in the future.