Graph-to-Tree Neural Networks for Learning Structured Input-Output Translation with Applications to Semantic Parsing and Math Word Problem

By Shucheng Li, Lingfei Wu, Shiwei Feng, Fangli Xu, Fengyuan Xu, Sheng Zhong. 2020

83 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Information Systems, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Sergey Levine
2. Lei Wang
3. Wei Dang Lu
4. Quoc V. Le
5. Yibin Shen
6. Cheqing Jin
7. Pieter Abbeel
8. Nakul Verma

In Information Systems

1. Bing Tian Dai
2. Yibin Shen
3. Cheqing Jin
4. Lei Wang
5. Dongxiang Zhang
6. Wei Dang Lu
7. Ee-Peng Lim
8. Zhanming Jie

In Natural Language Processing

1. Wei Dang Lu
2. Lei Wang
3. Jierui Li
4. Iddo Drori
5. Nakul Verma
6. Yibin Shen
7. Cheqing Jin
8. Bing Tian Dai

Citations in the corpus

• Training Verifiers to Solve Math Word Problems (2021, methodology): “…performance by designing specialized encoder-decoder architectures (Amini et al., 2019; Chiang and Chen, 2018; Xie and Sun, 2019; Chen et al., 2020; Li et al., 2020), with the strongest results often relying on large pretrained encoders from the BERT family (Chen et al., 2019; Kim et al., 2020;…”
• MWPToolkit: An Open-Source Framework for Deep Learning-Based Math Word Problem Solvers (2021, background): “Recently, a large number of new MWP solving methods have been proposed, including graph neural networks based (Li et al., 2020), template based (Lee et al.”
• Learning to Reason Deductively: Math Word Problem Solving as Complex Relation Extraction (2022, methodology): “Zhang et al. (2020) and Li et al. (2020) adopted a graph-to-tree approach to model the quantity relations using the graph convolutional networks (GCN) (Kipf and Welling, 2017).”
• Solving Math Word Problems with Multi-Encoders and Multi-Decoders (2020, background): “Graph2Tree considered the structure information of text descriptions, integrating the quantity cell graph and quantity comparison graph, so it achieves sub-optimal performance in all models.”
• Solving Linear Algebra by Program Synthesis (2021, methodology): “Techniques have included sequence-tosequence and graph-to-tree Transformers which achieve around 80% on Math23k and MAWPS datasets (Koncel-Kedziorski et al., 2016; Li et al., 2019; Wang et al., 2019; Zhang et al., 2020; Li et al., 2020; Wu et al., 2020; Qin et al., 2020; Lan et al., 2021).”
• A Survey of Deep Learning for Mathematical Reasoning (2022, unknown): “The graph-based information can also be embedded when encoding the input mathematical sequences (Zhang et al., 2020b; Shen and Jin, 2020; Li et al., 2020b; Wu et al., 2021a).”