论文标题
图形对树神经网络，用于学习结构化输入输出翻译，并应用于语义解析和数学单词问题
Graph-to-Tree Neural Networks for Learning Structured Input-Output Translation with Applications to Semantic Parsing and Math Word Problem
论文作者
论文摘要
著名的SEQ2SEQ技术及其众多变体在许多任务（例如神经机器翻译，语义解析和数学单词问题解决）方面具有出色的性能。但是，这些模型要么仅将输入对象视为序列，同时忽略了用于编码的重要结构信息，要么只是将输出对象视为序列输出而不是用于解码的结构对象。在本文中，我们提出了一个新颖的图形神经网络，即由图形编码器和分层树解码器组成的Graph2Tree，它编码增强的图形结构化输入并解码树结构化的输出。特别是，我们研究了解决两个问题的模型，即神经语义解析和数学单词问题。我们的广泛实验表明，我们的Graph2Tree模型优于这些任务上其他最先进模型的性能。
The celebrated Seq2Seq technique and its numerous variants achieve excellent performance on many tasks such as neural machine translation, semantic parsing, and math word problem solving. However, these models either only consider input objects as sequences while ignoring the important structural information for encoding, or they simply treat output objects as sequence outputs instead of structural objects for decoding. In this paper, we present a novel Graph-to-Tree Neural Networks, namely Graph2Tree consisting of a graph encoder and a hierarchical tree decoder, that encodes an augmented graph-structured input and decodes a tree-structured output. In particular, we investigated our model for solving two problems, neural semantic parsing and math word problem. Our extensive experiments demonstrate that our Graph2Tree model outperforms or matches the performance of other state-of-the-art models on these tasks.
