{"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/non-projective-dependency-parsing-via-latent","title":"Non-Projective Dependency Parsing via Latent Heads Representation (LHR)","arxiv_id":"1802.02116","date":"2018-02-06","proceeding":null,"authors":["Matteo Grella","Simone Cangialosi"],"abstract":"In this paper, we introduce a novel approach based on a bidirectional\nrecurrent autoencoder to perform globally optimized non-projective dependency\nparsing via semi-supervised learning. The syntactic analysis is completed at\nthe end of the neural process that generates a Latent Heads Representation\n(LHR), without any algorithmic constraint and with a linear complexity. The\nresulting \"latent syntactic structure\" can be used directly in other semantic\ntasks. The LHR is transformed into the usual dependency tree computing a simple\nvectors similarity. We believe that our model has the potential to compete with\nmuch more complex state-of-the-art parsing architectures.","url_abs":"http://arxiv.org/abs/1802.02116v1","url_pdf":"http://arxiv.org/pdf/1802.02116v1.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":"non-projective-dependency-parsing-via-latent","repo_url":"https://github.com/GrellaCangialosi/LHRParser","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"dependency-parsing","task_name":"Dependency Parsing"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}