Graph-to-Tree Neural Networks for Learning Structured Input-Output Translation with Applications to Semantic Parsing and Math Word Problem
arXiv:2004.13781
Abstract
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.
arXiv commentLong Paper in EMNLP 2020. 12 pages including references
References in corpus (13)
- Adam: A Method for Stochastic Optimization
- Sequence to Sequence Learning with Neural Networks
- Neural Message Passing for Quantum Chemistry
- Learning to Map Sentences to Logical Form: Structured Classification with Probabilistic Categorial Grammars
- Graph2Seq: Graph to Sequence Learning with Attention-based Neural Networks
- Learning to Represent Edits
- Reinforcement Learning Based Graph-to-Sequence Model for Natural Question Generation
- Sequence-to-Action: End-to-End Semantic Graph Generation for Semantic Parsing
- Data-Driven Methods for Solving Algebra Word Problems
- GraphFlow: Exploiting Conversation Flow with Graph Neural Networks for Conversational Machine Comprehension
- Exploiting Rich Syntactic Information for Semantic Parsing with Graph-to-Sequence Model
- SQL-to-Text Generation with Graph-to-Sequence Model
- Top-down Tree Structured Decoding with Syntactic Connections for Neural Machine Translation and Parsing