{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/a-gru-based-encoder-decoder-approach-with","title":"A GRU-based Encoder-Decoder Approach with Attention for Online Handwritten Mathematical Expression Recognition","arxiv_id":"1712.03991","date":"2017-12-04","proceeding":null,"authors":["Jianshu Zhang","Jun Du","Li-Rong Dai"],"abstract":"In this study, we present a novel end-to-end approach based on the\nencoder-decoder framework with the attention mechanism for online handwritten\nmathematical expression recognition (OHMER). First, the input two-dimensional\nink trajectory information of handwritten expression is encoded via the gated\nrecurrent unit based recurrent neural network (GRU-RNN). Then the decoder is\nalso implemented by the GRU-RNN with a coverage-based attention model. The\nproposed approach can simultaneously accomplish the symbol recognition and\nstructural analysis to output a character sequence in LaTeX format. Validated\non the CROHME 2014 competition task, our approach significantly outperforms the\nstate-of-the-art with an expression recognition accuracy of 52.43% by only\nusing the official training dataset. Furthermore, the alignments between the\ninput trajectories of handwritten expressions and the output LaTeX sequences\nare visualized by the attention mechanism to show the effectiveness of the\nproposed method.","url_abs":"http://arxiv.org/abs/1712.03991v1","url_pdf":"http://arxiv.org/pdf/1712.03991v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"a-gru-based-encoder-decoder-approach-with","repo_url":"https://github.com/JianshuZhang/TAP","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}