{"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/context-dependent-semantic-parsing-over","title":"Context-Dependent Semantic Parsing over Temporally Structured Data","arxiv_id":"1905.00245","date":"2019-05-01","proceeding":null,"authors":["Charles Chen","Razvan Bunescu"],"abstract":"We describe a new semantic parsing setting that allows users to query the\nsystem using both natural language questions and actions within a graphical\nuser interface. Multiple time series belonging to an entity of interest are\nstored in a database and the user interacts with the system to obtain a better\nunderstanding of the entity's state and behavior, entailing sequences of\nactions and questions whose answers may depend on previous factual or\nnavigational interactions. We design an LSTM-based encoder-decoder architecture\nthat models context dependency through copying mechanisms and multiple levels\nof attention over inputs and previous outputs. When trained to predict tokens\nusing supervised learning, the proposed architecture substantially outperforms\nstandard sequence generation baselines. Training the architecture using policy\ngradient leads to further improvements in performance, reaching a\nsequence-level accuracy of 88.7% on artificial data and 74.8% on real data.","url_abs":"http://arxiv.org/abs/1905.00245v1","url_pdf":"http://arxiv.org/pdf/1905.00245v1.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":"context-dependent-semantic-parsing-over","repo_url":"https://github.com/charleschen1015/SemanticParsing","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"semantic-parsing","task_name":"Semantic Parsing"},{"task_slug":"time-series-1","task_name":"Time Series"},{"task_slug":"time-series","task_name":"Time Series Analysis"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}