Computational Learning of Construction Grammars

[Read Full-Tex: Computational Learning of Construction Grammars] [Original Data: https://drive.google.com/open?id=0B6oBPlj4dynZTFlXV1JNbF9GNEE%5D [Current code: https://github.com/jonathandunn/c2xg%5D This paper presents an algorithm for learning the construction grammar of a language from a large corpus. This grammar induction algorithm has two goals: first, to show that construction grammars are learnable without highly specified innate structure; second, to develop a model … More Computational Learning of Construction Grammars

Multi-Unit Directional Measures of Association: Moving Beyond Pairs of Words

[Read Full Text: Dunn.Association Measures] [Data: https://drive.google.com/open?id=1Nc8huc0QEbNQ4WY3-4sqLVatbB0h0CC7%5D This paper formulates and evaluates a series of multi-unit measures of directional association, building on the pairwise ΔP measure, that are able to quantify association in sequences of varying length and type of representation. Multi-unit measures face an additional segmentation problem: once the implicit length constraint of pairwise … More Multi-Unit Directional Measures of Association: Moving Beyond Pairs of Words