Mapping natural-language problems to formal-language solutions using structured neural representations
Mapping natural-language problems to formal-language solutions using structured neural representations
复制标题
使用结构化神经表示将自然语言问题映射到形式语言解决方案
DOI：
--
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
Jianfeng Gao
中科院分区：
文献类型：
--
作者：
Kezhen Chen;Qiuyuan Huang;Hamid Palangi;P. Smolensky;Kenneth D. Forbus;Jianfeng Gao
生成由关系元素（例如LISP程序或数学操作）代表的正式语言程序，以解决自然语言所述的问题是一项挑战任务，因为它需要明确捕获输入中隐含的离散符号结构信息。请勿明确捕获此类结构信息，从而在本文中限制其性能。结构化神经表示，张量产物表示（TPRS），用于将自然语言问题映射到正式的语言解决方案，称为TPN2F。在符号空间中使用TPR“解开”，以关系元组为代表的顺序程序，每个程序由关系（或操作）和许多参数组成在两个基准上，基于LSTM的SEQ2SEQ模型的表现相当大，并创建了新的最先进的结果。 TPR如何增强TP-N2F的解释性。
Generating formal-language programs represented by relational tuples, such as Lisp programs or mathematical operations, to solve problems stated in natural language is a challenging task because it requires explicitly capturing discrete symbolic structural information implicit in the input. However, most general neural sequence models do not explicitly capture such structural information, limiting their performance on these tasks. In this paper, we propose a new encoder-decoder model based on a structured neural representation, Tensor Product Representations (TPRs), for mapping Natural-language problems to Formal-language solutions, called TPN2F. The encoder of TP-N2F employs TPR ‘binding’ to encode natural-language symbolic structure in vector space and the decoder uses TPR ‘unbinding’ to generate, in symbolic space, a sequential program represented by relational tuples, each consisting of a relation (or operation) and a number of arguments. TP-N2F considerably outperforms LSTM-based seq2seq models on two benchmarks and creates new state-of-the-art results. Ablation studies show that improvements can be attributed to the use of structured TPRs explicitly in both the encoder and decoder. Analysis of the learned structures shows how TPRs enhance the interpretability of TP-N2F.