Tree-Transformer: A Transformer-Based Method for Correction of Tree-Structured Data
This work addresses the lack of neural networks for tree-structured data correction, offering improvements in grammar correction tasks for domains like programming and linguistics, though it is incremental as it builds on transformer architectures.
The authors tackled the problem of correcting tree-structured data, such as source code and natural language, by introducing the Tree-Transformer, a neural network architecture for translating between input and output trees. The model achieved a 25% F0.5 improvement over the best sequential method on source code and a 10% recall improvement on the CoNLL 2014 benchmark, with a state-of-the-art F0.5 score of 50.43 on the AESW benchmark.
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 $50.43$.