{"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/alignment-based-compositional-semantics-for","title":"Alignment-based compositional semantics for instruction following","arxiv_id":"1508.06491","date":"2015-08-26","proceeding":"EMNLP 2015 9","authors":["Jacob Andreas","Dan Klein"],"abstract":"This paper describes an alignment-based model for interpreting natural\nlanguage instructions in context. We approach instruction following as a search\nover plans, scoring sequences of actions conditioned on structured observations\nof text and the environment. By explicitly modeling both the low-level\ncompositional structure of individual actions and the high-level structure of\nfull plans, we are able to learn both grounded representations of sentence\nmeaning and pragmatic constraints on interpretation. To demonstrate the model's\nflexibility, we apply it to a diverse set of benchmark tasks. On every task, we\noutperform strong task-specific baselines, and achieve several new\nstate-of-the-art results.","url_abs":"http://arxiv.org/abs/1508.06491v2","url_pdf":"http://arxiv.org/pdf/1508.06491v2.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":"alignment-based-compositional-semantics-for","repo_url":"https://github.com/jacobandreas/instructions","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"instruction-following","task_name":"Instruction Following"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1508.06491","atlas_url":"https://app.syntology.ai/?focus=1508.06491","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}