Litcius/Paper detail

A Tree-Structured Decoder for Image-to-Markup Generation

Jianshu Zhang, Jun Du, Yongxin Yang, Yi-Zhe Song, Si Wei, Li-Rong Dai

2020Surrey Research Insight Open Access (The University of Surrey)26 citations

Abstract

Recent encoder-decoder approaches typically employ string decoders to convert images into serialized strings for image-to-markup. However,
\nfor tree-structured representational markup, string
\nrepresentations can hardly cope with the structural complexity. In this work, we first show
\nvia a set of toy problems that string decoders
\nstruggle to decode tree structures, especially as
\nstructural complexity increases, we then propose
\na tree-structured decoder that specifically aims
\nat generating a tree-structured markup. Our decoders works sequentially, where at each step a
\nchild node and its parent node are simultaneously
\ngenerated to form a sub-tree. This sub-tree is consequently used to construct the final tree structure
\nin a recurrent manner. Key to the success of our
\ntree decoder is twofold, (i) it strictly respects the
\nparent-child relationship of trees, and (ii) it explicitly outputs trees as oppose to a linear string.
\nEvaluated on both math formula recognition and
\nchemical formula recognition, the proposed tree
\ndecoder is shown to greatly outperform strong
\nstring decoder baselines.

Topics & Concepts

Markup languageTree (set theory)Computer scienceNode (physics)TrieString (physics)EncoderTheoretical computer scienceK-ary treeSearch treeTree structureSet (abstract data type)Decoding methodsAlgorithmBinary treeData structureMathematicsCombinatoricsXMLProgramming languageMathematical physicsStructural engineeringEngineeringOperating systemSearch algorithmHandwritten Text Recognition TechniquesMultimodal Machine Learning ApplicationsTopic Modeling
A Tree-Structured Decoder for Image-to-Markup Generation | Litcius