D14-1004 discriminative approach to selectional preference acquisition . Positive examples are taken
D14-1004 preference acquisition . Selectional preference acquisition using neural networks has not
D14-1004 co-compositionality . Our model for selectional preference acquisition uses a network architecture that
D14-1004 clustering algorithm for selectional preference acquisition based on a probabilistic latent
S01-1029 training data for selectional preference acquisition . At run-time the preprocessor
D14-1004 existing models for selectional preference acquisition . Finally , section 5 concludes
D14-1004 standard ( two-way ) selectional preference acquisition . Selectional preference acquisition
D14-1004 architecture for three-way selectional preference acquisition to the results of the tensor-based
J03-4004 training data for selectional preference acquisition , it produces the single highest-ranked
Q14-1035 frame detection , and selectional preference acquisition . The second game , Ka-boom !
D14-1004 work with respect to selectional preference acquisition and neural network modeling .
D14-1004 network approach to selectional preference acquisition using verb-object tuples for
P10-3013 <title> Automatic Selectional Preference Acquisition for Latin verbs </title> Barbara
P98-2247 in alternations . 3 Selectional Preference Acquisition Selectional preferences can be
D14-1004 based-approach for multi-way selectional preference acquisition to this tensor-based factorization
D14-1004 Network Approach to Selectional Preference Acquisition </title> Tim Van_de Abstract
C04-1133 initial results . 1.1 Selectional Preference Acquisition : Current State of the Art Predicate
C04-1133 disam - biguation , selectional preference acquisition , as well as anaphora resolution
J03-4004 the test data . 3.3 Selectional Preference Acquisition The preferences are acquired
D14-1111 classic problem of selectional preference acquisition , since the design of the pseudo-disambiguation
hide detail