{"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/learning-structured-text-representations","title":"Learning Structured Text Representations","arxiv_id":"1705.09207","date":"2017-05-25","proceeding":"TACL 2018 1","authors":["Yang Liu","Mirella Lapata"],"abstract":"In this paper, we focus on learning structure-aware document representations\nfrom data without recourse to a discourse parser or additional annotations.\nDrawing inspiration from recent efforts to empower neural networks with a\nstructural bias, we propose a model that can encode a document while\nautomatically inducing rich structural dependencies. Specifically, we embed a\ndifferentiable non-projective parsing algorithm into a neural model and use\nattention mechanisms to incorporate the structural biases. Experimental\nevaluation across different tasks and datasets shows that the proposed model\nachieves state-of-the-art results on document modeling tasks while inducing\nintermediate structures which are both interpretable and meaningful.","url_abs":"http://arxiv.org/abs/1705.09207v4","url_pdf":"http://arxiv.org/pdf/1705.09207v4.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":"learning-structured-text-representations","repo_url":"https://github.com/nlpyang/structured","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"learning-structured-text-representations","repo_url":"https://github.com/JepsonWong/Text_Classification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"learning-structured-text-representations","repo_url":"https://github.com/elisaF/structured","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1705.09207","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}