Paper Info
Title
Tree-Structured Neural Machine for Linguistics-Aware Sentence 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 t 1.15% increase of acceptance ratio.
Year
Venue
Field
2018
THIRTY-SECOND AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTIETH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / EIGHTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE
Computer science,Natural language processing,Artificial intelligence,Sentence generation,Machine learning
DocType
Citations 
PageRank 
Conference
0
0.34
References 
Authors
17
7
Name
Order
Citations
PageRank
Ganbin Zhou110.69
Ping Luo283953.92
rongyu cao3204.24
Yijun Xiao4233.54
Fen Lin515319.00
bo chen63120.10
Qing He775480.58