树结构上的长短期记忆
Long Short-Term Memory Over Tree Structures
摘要：
链式结构的长短期记忆（LSTM）已被证明在语音识别和机器翻译等广泛问题中有效。在本文中，我们建议将其扩展到树结构，其中一个存储单元可以反映历史的记忆多个子细胞或多个后代细胞在递归过程中。我们称之为S-LSTM模型，它提供了一种考虑层次结构上的长距离交互的原则性方法，例如，语言或图像解析结构。我们利用语义组合模型来理解文本的含义，这是自然语言理解中的一个基本问题，并通过将其组合层替换为S-LSTM内存块来证明它优于最先进的递归模型。我们还表明，利用给定的结构是有助于实现更好的性能比不考虑的结构。
英文摘要：
The chain-structured long short-term memory (LSTM) has showed to be effective in a wide range of problems such as speech recognition and machine translation. In this paper, we propose to extend it to tree structures, in which a memory cell can reflect the history memories of multiple child cells or multiple descendant cells in a recursive process. We call the model S-LSTM, which provides a principled way of considering long-distance interaction over hierarchies, e.g., language or image parse structures. We leverage the models for semantic composition to understand the meaning of text, a fundamental problem in natural language understanding, and show that it outperforms a state-of-the-art recursive model by replacing its composition layers with the S-LSTM memory blocks. We also show that utilizing the given structures is helpful in achieving a performance better than that without considering the structures.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
