Tree-Structured Neural Machine for Linguistics-Aware Sentence Generation

Authors

  • Ganbin Zhou Institute of Computing Technology, Chinese Academy of Sciences
  • Ping Luo Institute of Computing Technology, Chinese Academy of Sciences
  • Rongyu Cao Institute of Computing Technology, Chinese Academy of Sciences
  • Yijun Xiao Department of Computer Science, University of California Santa Barbara
  • Fen Lin WeChat Search Application Department, Tencent
  • Bo Chen WeChat Search Application Department, Tencent
  • Qing He Institute of Computing Technology, Chinese Academy of Sciences

Keywords:

tree-structured neural network, dialog generation

Abstract

Different from other sequential data, sentences in natural language are structured by linguistic grammars. Previous generative conversational models with chain-structured decoder ignore this structure in human language and might generate plausible responses with less satisfactory relevance and fluency. In this study, we aim to incorporate the results from linguistic analysis into the process of sentence generation for high-quality conversation generation. Specifically, we use a dependency parser to transform each response sentence into a dependency tree and construct a training corpus of sentence-tree pairs. A tree-structured decoder is developed to learn the mapping from a sentence to its tree, where different types of hidden states are used to depict the local dependencies from an internal tree node to its children. For training acceleration, we propose a tree canonicalization method, which transforms trees into equivalent ternary trees. Then, with a proposed tree-structured search method, the model is able to generate the most probable responses in the form of dependency trees, which are finally flattened into sequences as the system output. Experimental results demonstrate that the proposed X2Tree framework outperforms baseline methods over 11.15% increase of acceptance ratio.

Downloads

Published

2018-04-27

How to Cite

Zhou, G., Luo, P., Cao, R., Xiao, Y., Lin, F., Chen, B., & He, Q. (2018). Tree-Structured Neural Machine for Linguistics-Aware Sentence Generation. Proceedings of the AAAI Conference on Artificial Intelligence, 32(1). Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/11969