Abstract | ||
---|---|---|
Blanco & Moldovan (Blanco and Moldovan, 2011) have empirically demonstrated that negated sentences often convey implicit positive inferences, or focus, and that these inferences are both human annotatable and machine learnable. Concentrating on their annotation process, this paper argues that the focus-based implicit positivity should be separated from concepts of scalar implicature and neg-raising, as well as the placement of stress. We show that a model making these distinctions clear and which incorporates the pragmatic notion of question under discussion yields κ rates above .80, but that it substantially deflates the rates of focus of negation in text. |
Year | Venue | Keywords |
---|---|---|
2012 | ExProM@ACL | discussion yield,annotation process,machine learnable,focus-based implicit positivity,implicit positive inference,scalar implicature,pragmatic notion,human annotatable,computational linguistics,natural language,semantics |
Field | DocType | Volume |
Annotation,Negation,Computer science,Romanian,Computational linguistics,Natural language,Artificial intelligence,Natural language processing,Linguistics,Semantics,Scalar implicature | Conference | W12-38 |
Citations | PageRank | References |
2 | 0.37 | 1 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Pranav Anand | 1 | 260 | 19.70 |
Craig H. Martell | 2 | 211 | 39.69 |