http://rdf.ncbi.nlm.nih.gov/pubchem/patent/JP-2004029968-A

Outgoing Links

Predicate Object
assignee http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_05122eae7fa9154d47147a444ef69c26
classificationIPCInventive http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06F17-15
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06F17-28
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06F17-27
filingDate 2002-06-21-04:00^^<http://www.w3.org/2001/XMLSchema#date>
inventor http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_a6a7375a525a1d47830c831128b8d1bf
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_578ade6812083c3c814314047546bf58
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_c3991e25844ecda49eeaf8edf4d1d7c8
publicationDate 2004-01-29-04:00^^<http://www.w3.org/2001/XMLSchema#date>
publicationNumber JP-2004029968-A
titleOfInvention Topic estimation model generation method and topic estimation method
abstract An object of the present invention is to provide a method for generating a topic estimation model that can be applied to dialogue expression using spoken words and that can estimate a topic to which an input utterance sentence belongs with one utterance unit and with good accuracy. A relevance between a word and each topic item is determined for each word appearing in the learning dialogue based on a plurality of learning dialogues to which predefined topic items are assigned and morphologically analyzed. , Calculated from the mutual information between the word and the topic item and the entropy related to the word appearance, and generates a table storing the degree of relevance to each topic item for each word. [Selection diagram] Fig. 4
isCitedBy http://rdf.ncbi.nlm.nih.gov/pubchem/patent/JP-2014178965-A
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-107977363-A
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-108021558-A
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-107622051-A
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-107977363-B
priorityDate 2002-06-21-04:00^^<http://www.w3.org/2001/XMLSchema#date>
type http://data.epo.org/linked-data/def/patent/Publication

Incoming Links

Predicate Subject
isDiscussedBy http://rdf.ncbi.nlm.nih.gov/pubchem/substance/SID453095146
http://rdf.ncbi.nlm.nih.gov/pubchem/compound/CID161104

Total number of triples: 21.