{"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/amuse-multilingual-semantic-parsing-for","title":"AMUSE: Multilingual Semantic Parsing for Question Answering over Linked Data","arxiv_id":"1802.09296","date":"2018-02-26","proceeding":null,"authors":["Sherzod Hakimov","Soufian Jebbara","Philipp Cimiano"],"abstract":"The task of answering natural language questions over RDF data has received\nwide interest in recent years, in particular in the context of the series of\nQALD benchmarks. The task consists of mapping a natural language question to an\nexecutable form, e.g. SPARQL, so that answers from a given KB can be extracted.\nSo far, most systems proposed are i) monolingual and ii) rely on a set of\nhard-coded rules to interpret questions and map them into a SPARQL query. We\npresent the first multilingual QALD pipeline that induces a model from training\ndata for mapping a natural language question into logical form as probabilistic\ninference. In particular, our approach learns to map universal syntactic\ndependency representations to a language-independent logical form based on\nDUDES (Dependency-based Underspecified Discourse Representation Structures)\nthat are then mapped to a SPARQL query as a deterministic second step. Our\nmodel builds on factor graphs that rely on features extracted from the\ndependency graph and corresponding semantic representations. We rely on\napproximate inference techniques, Markov Chain Monte Carlo methods in\nparticular, as well as Sample Rank to update parameters using a ranking\nobjective. Our focus lies on developing methods that overcome the lexical gap\nand present a novel combination of machine translation and word embedding\napproaches for this purpose. As a proof of concept for our approach, we\nevaluate our approach on the QALD-6 datasets for English, German & Spanish.","url_abs":"http://arxiv.org/abs/1802.09296v1","url_pdf":"http://arxiv.org/pdf/1802.09296v1.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":"amuse-multilingual-semantic-parsing-for","repo_url":"https://github.com/ag-sc/AMUSE","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"form","task_name":"Form"},{"task_slug":"knowledge-base-question-answering","task_name":"Knowledge Base Question Answering"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"semantic-parsing","task_name":"Semantic Parsing"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1802.09296","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}