W15-2308 on the idea generically called distributional learning . Those techniques have been
P08-1090 debate over appropriate metrics for distributional learning , we also experimented with the
W06-2916 heuristics to improve the efficiency of distributional learning . However , in tests over a large
W06-2916 results . This work focuses on distributional learning from raw text . Various models
W15-2308 languages is denoted by L ( E ) . Distributional learning is concerned with what X - derivation
W14-1620 . It is clear , however , that distributional learning can not account for the entire
W10-2904 arguments together suggest that distributional learning has a somewhat privileged status
W13-2602 <title> A model of generalization in distributional learning of phonetic categories </title>
W06-2916 generalization is not sufficient to support distributional learning . We might expect this : attempting
W13-2602 features of human per - formance : distributional learning and generaliza - tion . We model
W06-2916 learning There are many issues with distributional learning , especially when learning from
W06-2916 propose an extension to strict distributional learning that incorporates more information
P08-1090 Our algorithm is an unsupervised distributional learning approach that uses coreferring
W09-1006 correspond to the contexts that distributional learning algorithms can infer the structure
W14-0506 In recent years , a theory of distributional learning of phrase structure grammars
W14-0506 modeling of segmentation . <title> Distributional Learning as a Theory of Language </title>
W06-2916 efficiency constraints . 3 Issues for distributional learning There are many issues with distributional
W10-2904 after some basic discussion of distributional learning in Section 2 , we define in Section
W14-0506 language acquisition based on distributional learning and sketch some of the nontrivial
W10-2904 are a number of reasons to take distributional learning seriously : first , historically
hide detail