{"pk":28558,"title":"Applying Deep Language Understanding to Open Text:Lessons Learned","subtitle":null,"abstract":"Human-level natural language understanding (NLU) of opentext is far beyond the current state of the art. In practice, ifdeep NLU is attempted at all, it is within narrow domains. Wereport a program of R&D on cognitively modeled NLU thatworks toward depth and breadth of processing simultaneous-ly. The current contribution describes lessons learned – scien-tifically and methodologically – from an exercise in applyingdeep NLU to open-domain texts. An overarching lesson wasthat although learning to compute sentence-level semanticsseems like a natural step toward computing full, context-sensitive, semantic and pragmatic meaning, corpus evidenceunderscores just how infrequently semantics can be cleanlyseparated from pragmatics. We conclude that a more compre-hensive methodology for automatic example selection and re-sult validation is needed as prerequisite for success in devel-oping NLU applications operating on open text.","language":"eng","license":{"name":"","short_name":"","text":null,"url":""},"keywords":[{"word":"natural language understanding; cognitive model-ing; language-endowed intelligent agents"}],"section":"Papers with Oral Presentations","is_remote":true,"remote_url":"https://escholarship.org/uc/item/7th0w0q8","frozenauthors":[{"first_name":"Marjorie","middle_name":"","last_name":"McShane","name_suffix":"","institution":"Rensselaer Polytechnic Institute","department":""},{"first_name":"Stephen","middle_name":"","last_name":"Beale","name_suffix":"","institution":"Rensselaer Polytechnic Institute","department":""},{"first_name":"Irene","middle_name":"","last_name":"Nirenburg","name_suffix":"","institution":"Rensselaer Polytechnic Institute","department":""}],"date_submitted":null,"date_accepted":null,"date_published":"2019-01-01T18:00:00Z","render_galley":null,"galleys":[{"label":"PDF","type":"pdf","path":"https://journalpub.escholarship.org/cognitivesciencesociety/article/28558/galley/18429/download/"}]}