{"pk":31783,"title":"Establishing Long-Distance Dependencies in a Hypbrid Network Model of Human Parsing","subtitle":null,"abstract":"This paper presents CAPERS, a hybrid spreading ac-\ntivation/marker pjissing architecture for parsing, whose\nself-processing network directly represents a parse tree.\nC A P E R S establishes syntactic dependencies through the\npurely local communication of simple syntactic features\nwithin the network. The structural constraints on two\nnodes in a long-distance syntactic relation are broken\ndown into locsil components, each of which can be ver-\nified entirely between pairs of adjacent nodes along the\nfeature passing path between the two dependent nodes.\nThis method of establishing long-distance syntactic rela-\ntions, in conjunction with the competitive dynamics of\nthe network, accounts for psycholinguistic experimental\ndata onfiller/gap constructions.","language":"eng","license":{"name":"","short_name":"","text":null,"url":""},"keywords":[],"section":"Submitted Presentations","is_remote":true,"remote_url":"https://escholarship.org/uc/item/3nf4n1rd","frozenauthors":[{"first_name":"Suzanne","middle_name":"","last_name":"Stevenson","name_suffix":"","institution":"University of Toronto","department":""}],"date_submitted":null,"date_accepted":null,"date_published":"1993-01-01T18:00:00Z","render_galley":null,"galleys":[{"label":"PDF","type":"pdf","path":"https://journalpub.escholarship.org/cognitivesciencesociety/article/31783/galley/22851/download/"}]}