{"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/seq2rdf-an-end-to-end-application-for","title":"Seq2RDF: An end-to-end application for deriving Triples from Natural Language Text","arxiv_id":"1807.01763","date":"2018-07-04","proceeding":null,"authors":["Yue Liu","Tongtao Zhang","Zhicheng Liang","Heng Ji","Deborah L. McGuinness"],"abstract":"We present an end-to-end approach that takes unstructured textual input and\ngenerates structured output compliant with a given vocabulary. Inspired by\nrecent successes in neural machine translation, we treat the triples within a\ngiven knowledge graph as an independent graph language and propose an\nencoder-decoder framework with an attention mechanism that leverages knowledge\ngraph embeddings. Our model learns the mapping from natural language text to\ntriple representation in the form of subject-predicate-object using the\nselected knowledge graph vocabulary. Experiments on three different data sets\nshow that we achieve competitive F1-Measures over the baselines using our\nsimple yet effective approach. A demo video is included.","url_abs":"http://arxiv.org/abs/1807.01763v3","url_pdf":"http://arxiv.org/pdf/1807.01763v3.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":"seq2rdf-an-end-to-end-application-for","repo_url":"https://github.com/YueLiu/NeuralTripleTranslation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"seq2rdf-an-end-to-end-application-for","repo_url":"https://github.com/abhinavnagpal/KNOWLEDGE-GRAPH-PAPERS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"seq2rdf-an-end-to-end-application-for","repo_url":"https://github.com/webnlg/webnlg-text-to-triples","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"knowledge-graph-embeddings","task_name":"Knowledge Graph Embeddings"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1807.01763","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}