Tree-Transformer: A Transformer-Based Method for Correction of Tree-Structured Data

Abstract

Many common sequential data sources, such as source code and natural language, have a natural tree-structured representation. These trees can be generated by fitting a sequence to a grammar, yielding a hierarchical ordering of the tokens in the sequence. This structure encodes a high degree of syntactic information, making it ideal for problems such as grammar correction. However, little work has been done to develop neural networks that can operate on and exploit tree-structured data. In this paper we present the Tree-Transformer \textemdash{} a novel neural network architecture designed to translate between arbitrary input and output trees. We applied this architecture to correction tasks in both the source code and natural language domains. On source code, our model achieved an improvement of $25\%$ $\text{F}0.5$ over the best sequential method. On natural language, we achieved comparable results to the most complex state of the art systems, obtaining a $10\%$ improvement in recall on the CoNLL 2014 benchmark and the highest to date $\text{F}0.5$ score on the AESW benchmark of $50.43$.

References in corpus (6)

• Neural Language Correction with Character-Based Attention
• Neuro-Symbolic Program Synthesis
• A Multilayer Convolutional Encoder-Decoder Neural Network for Grammatical Error Correction
• Long Short-Term Memory Over Tree Structures
• Learning to Repair Software Vulnerabilities with Generative Adversarial Networks
• Semantic Code Repair using Neuro-Symbolic Transformation Networks

Cited by in corpus (9)

• Unified Pre-training for Program Understanding and Generation
• A Transformer-based Approach for Source Code Summarization
• Code Prediction by Feeding Trees to Transformers
• Tree-structured Attention with Hierarchical Accumulation
• SentiBERT: A Transferable Transformer-Based Architecture for Compositional Sentiment Semantics
• Code Summarization with Structure-induced Transformer
• Integrating Visuospatial, Linguistic and Commonsense Structure into Story Visualization
• CodeQA: A Question Answering Dataset for Source Code Comprehension
• Structured Context and High-Coverage Grammar for Conversational Question Answering over Knowledge Graphs