Pessoal,
Segue abaixo convite para seminário online da Escola de Matemática Aplicada da FGV, nesta quinta-feira as 16h. Valeria irá falar de GraphKR, uma abordagem para 'meaning representation’ de linguagens naturais. Seminário é aberto, link para inscrição no final do email, peço que repassem e ajudem na divulgação. Ab., Alexandre ===== Titulo: GraphKR Semantic Parsing for Portuguese Palestrante: Valeria de Paiva Resumo: Semantic parsing to construct graphical meaning representations is an active topic of research at the moment. Representation languages such as AMR, Alexa Meaning Language, Deep Universal Dependencies are some examples and these are getting more accurate as time goes by, and more annotations are accumulated.Traditional, old fashioned Natural Language Understanding uses logic and knowledge representation to build-up meaning representations, that are more useful, as one can reason with them. But these have a reputation for being brittle, hard to build and not easy to improve. We would like hybrid systems that keep the best of both worlds. Three broad approaches have been attempted to combine distributional and structural/symbolic aspects of meaning representation construction: a) injecting linguistic features into distributional representations, b) injecting distributional features into symbolic representations or c) combining structural and distributional features in the final representation. This work focuses on an example of the third and less studied approach: it extends the Graphical Knowledge Representation (GKR) of Crouch and Kalouli to include distributional features and proposes a division of semantic labour between the distributional and structural/symbolic features. While the work presented last year proposed two extensions of GKR to clearly show this division of labour and empirically test one of the proposals on an NLI dataset with hard compositional pairs, in this talk we discuss the possibilities and difficulties of extending this work from English to Portuguese. GKR demo online at http://lap0973.sprachwiss.uni-konstanz.de:8080/sem.mapper/ Minibio: Valeria de Paiva is a mathematician and computer scientist based in Cupertino, CA. She's working on a 'stealth' start-up in Berkeley, the Topos Institute, while 'visiting' the Department of Informatica, PUC-Rio de Janeiro. She worked as a Principal Scientist at Samsung Research America, and as a senior applied scientist at Nuance Communications, Sunnyvale, CA. Earlier she was at Rearden Commerce and she was a search analyst at Cuil, Inc. in Menlo Park, CA. Before that, she was a research scientist at the Intelligent Systems Laboratory of PARC (Palo Alto Research Center), California (2000-2008). She received her Ph.D. in Mathematics from Cambridge University in 1988 for work on "Dialectica Categories", under Martin Hyland's supervision, and has ever since worked on logical approaches to computation, especially using Category Theory. Olá! Você foi convidado para uma reunião do(a) Zoom. Quando: 1 out 2020 04:00 PM São Paulo Inscreva-se antecipadamente para esta reunião: https://ide-fgv-br.zoom.us/meeting/register/tJclceygrD4vGNQGsydh6omKYBi519NDspWy Após a inscrição, você receberá um e-mail de confirmação contendo informações sobre como entrar na reunião. -- Você está recebendo esta mensagem porque se inscreveu no grupo "LOGICA-L" dos Grupos do Google. Para cancelar inscrição nesse grupo e parar de receber e-mails dele, envie um e-mail para logica-l+unsubscr...@dimap.ufrn.br. Para ver esta discussão na web, acesse https://groups.google.com/a/dimap.ufrn.br/d/msgid/logica-l/2A618C25-49F6-44F2-8497-3E13CED6004E%40gmail.com.
