{"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/amr-parsing-as-graph-prediction-with-latent","title":"AMR Parsing as Graph Prediction with Latent Alignment","arxiv_id":"1805.05286","date":"2018-05-14","proceeding":"ACL 2018 7","authors":["Chunchuan Lyu","Ivan Titov"],"abstract":"Abstract meaning representations (AMRs) are broad-coverage sentence-level\nsemantic representations. AMRs represent sentences as rooted labeled directed\nacyclic graphs. AMR parsing is challenging partly due to the lack of annotated\nalignments between nodes in the graphs and words in the corresponding\nsentences. We introduce a neural parser which treats alignments as latent\nvariables within a joint probabilistic model of concepts, relations and\nalignments. As exact inference requires marginalizing over alignments and is\ninfeasible, we use the variational auto-encoding framework and a continuous\nrelaxation of the discrete alignments. We show that joint modeling is\npreferable to using a pipeline of align and parse. The parser achieves the best\nreported results on the standard benchmark (74.4% on LDC2016E25).","url_abs":"http://arxiv.org/abs/1805.05286v1","url_pdf":"http://arxiv.org/pdf/1805.05286v1.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":"amr-parsing-as-graph-prediction-with-latent","repo_url":"https://github.com/ChunchuanLv/AMR_AS_GRAPH_PREDICTION","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"amr-parsing-as-graph-prediction-with-latent","repo_url":"https://github.com/josefigueroa168/NLP-project","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"amr-parsing","task_name":"AMR Parsing"},{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/amr-parsing-on-ldc2015e86-1","task":"AMR Parsing","dataset":"LDC2015E86","model":"Joint model","rank_in_archive_order":1,"of":6,"metrics":{"Smatch":"73.7"},"uses_additional_data":false},{"leaderboard":"/sota/amr-parsing-on-ldc2017t10","task":"AMR Parsing","dataset":"LDC2017T10","model":"Joint model","rank_in_archive_order":23,"of":27,"metrics":{"Smatch":"74.4"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1805.05286","atlas_url":"https://app.syntology.ai/?focus=1805.05286","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}