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

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

1 Jan 2020ICML 2020 1archive 2025-07-28

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

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

PaperPDFConference PDFCode

Code

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

DecoderHandwritten Mathmatical Expression RecognitionMath

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Handwritten Mathmatical Expression Recognition CROHME 2014 TD ExpRate 49.1 #16 of 17 Archive leaderboard report
Handwritten Mathmatical Expression Recognition CROHME 2016 TD ExpRate 48.5 #14 of 16 Archive leaderboard report
Handwritten Mathmatical Expression Recognition CROHME 2019 TD ExpRate 51.4 #13 of 14 Archive leaderboard report
Handwritten Mathmatical Expression Recognition HME100K TD ExpRate 62.6 #11 of 12 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections