J13-1008 complex syntactic patterns , and embedding useful morphological features
D15-1031 We study the problem of jointly embedding a knowledge base and a text corpus
C86-1088 who owns a book reads it . The embedding rule for = > - conditions
D15-1191 Abstract We consider the problem of embedding knowledge graphs ( KGs ) into
W05-0627 the largest probability among embedding ones are kept . After predicting
P14-1011 learns how to transform semantic embedding space in one language to the
C86-1008 axiomatic theory of dialogue , embedding rhetorical patterns , focusing
J10-3010 extrinsic evaluation is done by embedding the expansion systems into a
P15-1107 and words , then decodes this embedding to reconstruct the original paragraph
H91-1024 there is , for example , much more embedding of requests in hypotheticals
J80-1001 grammars have a straightforward embedding , but which permit various transformations
D14-1062 relevance for the in-domain task . By embedding our latent domain phrase model
J09-1002 TransType ideas , the innovative embedding proposed here consists in using
C86-1088 . The analysis is completed by embedding the DRS representing the text
D15-1205 </title> R Abstract Compositional embedding models build a representation
D15-1036 result in different orderings of embedding methods , calling into question
D15-1054 application of conventional word embedding methodologies for ad click prediction
P15-1125 large-scale knowledge bases . The novel embedding model associates each category
P15-1009 lie close to each other in the embedding space . Two manifold learning
J82-3001 different . The intuitive notion of " embedding a linguistic theory into a model
hide detail