Báo cáo khoa học: "Improving Name Tagging by Reference Resolution and Relation Detection" docx
... mention: a reference to an entity (typically, a noun phrase) name mention: a reference by name to an entity nominal mention: a reference by a common noun or noun phrase to an entity relation: ... according to the current reference resolution results 5.1 Coreference Features For each mention we compute seven quantities based on the results of name tagging and...
Ngày tải lên: 23/03/2014, 19:20
... similarity between w and any word in D j . In this paper we choose lin (Lin, 1998) and jcn (Jiang and Conrath, 1997) to compute the word-to-word semantic similarity. We only choose nouns and verbs for ... methods to measure the similar- ity between question and candidate answers. The candidate answers were ranked based on the hidden topics discovered by Latent Dirichlet Allocation...
Ngày tải lên: 23/03/2014, 16:20
... not V 1 and V 2 and A 2 > a 3 and P 2 < a 4 and S 1 -S 2 < a 5 and S 2 > a 6 , return C 2 7. If V 1 and V 2 and (A 2 - P 2 /a 7 ) > (A 1 - P 1 /a 7 ) and A 1 ... C 1 = nil and V 2 , return C 2 2. If V 1 and A 1 > a 1 , return C 1 3. If not V 1 and not V 2 and type(T) ∈ MUSTCONSTRAIN, return nil 4. If not V 1 and n...
Ngày tải lên: 23/03/2014, 18:20
Tài liệu Báo cáo khoa học: "Improving Word Representations via Global Context and Multiple Word Prototypes" pdf
... embeddings that better capture the se- mantics of words by incorporating both local and global document context, and 2) accounts for homonymy and polysemy by learning mul- tiple embeddings per word. We ... to capture homonymy and polysemy. Reisinger and Mooney (2010b) introduced a multi-prototype VSM where word sense discrimination is first applied by clus- tering contexts, an...
Ngày tải lên: 19/02/2014, 19:20
Báo cáo khoa học: "Fast Full Parsing by Linear-Chain Conditional Random Fields" docx
... used the IOB tagging method to represent chunks and memory-based learning, and achieved an f-score of 80.49 on the WSJ corpus. Tsuruoka and Tsu- jii (2005) improved upon their approach by using 1 The ... identical to shallow parsing by CRFs, we follow the feature sets used in the previous work by Sha and Pereira (2003). We use unigrams, bigrams, and trigrams of part-of-speec...
Ngày tải lên: 17/03/2014, 22:20
Báo cáo khoa học: "Improving Automatic Indexing through Concept Combination and Term Enrichment" ppt
... document, and, (3) interweave controlled indexing, free indexing, and thesaurus acquisition. These 3 goals are achieved by CONPARS (CONceptual PARSer), presented in this paper and illustrated by ... indexes i and j and their syntactic heads H(i) and H(j): Definition 3.1 (Index priority) Let i and j be two indexes in the same sentence. The rela- tive priority ranking...
Ngày tải lên: 31/03/2014, 04:20
Tài liệu Báo cáo khoa học: " Applying Co-Training to Reference Resolution" ppt
... used by Cardie and Wagstaff The feature semantic class used by Cardie and Wagstaff (1999) seems to be a domain-dependent one which can only be used for the MUC domain and similar ones. Cardie and ... between anaphor and antecedent – semantic class agreement between anaphor and an- tecedent – gender agreement between anaphor and antecedent – anaphor and antecedent are both...
Ngày tải lên: 20/02/2014, 21:20
Báo cáo khoa học: "A Flexible Architecture for Reference Resolution" docx
... Flexible Architecture for Reference Resolution Donna K. Byron and Joel R. Tetreault Department of Computer Science University of Rochester Rochester NY 14627, U.S.A. dbyron/tetreaul@cs, rochester, ... evaluation cor- pus, but pronoun resolution modules and meth- ods for combining their results were activated and de-activated by the genetic algorithm. Using pro- noun r...
Ngày tải lên: 08/03/2014, 21:20
Báo cáo khoa học: "ON THE INDEPENDENCE OF DISCOURSE STRUCTURE AND SEMANTIC DOMAIN" docx
... the layout by successive mention of each room and its position. This tour forms a tree composed of the entry to the apartment as root with the rooms and their locations as nodes, and with an ... planning by a small group, the tree is not constructed exclusively by addition, as are the types discussed above. Deletion, substitution, and movement also occur, as a plan is cr...
Ngày tải lên: 17/03/2014, 19:20
Báo cáo khoa học: Systems biology: experimental design Clemens Kreutz and Jens Timmer docx
... errors is ‘randomization’. Randomization means both, a random allocation of the experimental material and a random order in which the individual runs of the experiment are performed. Randomization ... efficient experimental planning requires that, on the one hand, theoreticians are able to appraise experimental feasi- bility and efforts and that, on the other hand, experi- menters know w...
Ngày tải lên: 23/03/2014, 06:20