| Predicate |
Object |
| assignee |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_bea649f68e7b959a0faa907abe00d40e |
| classificationCPCInventive |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F40-30
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F40-247
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-044
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-04
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-045
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F40-56
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F17-18
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F40-117
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N5-022
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F40-58
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F16-2237
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F16-3347
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F40-289
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-082 |
| classificationIPCInventive |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06F17-27
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06F17-28 |
| filingDate |
2018-05-15^^<http://www.w3.org/2001/XMLSchema#date> |
| inventor |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_7866cbe797f1b1414fd3de8b7f1d46d8
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_e740254499e93102cc14176362518880
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_e545fd3bca7d7c2d4e936cccc28252e4 |
| publicationDate |
2019-10-10^^<http://www.w3.org/2001/XMLSchema#date> |
| publicationNumber |
AU-2018270241-A1 |
| titleOfInvention |
Neural paraphrase generator |
| abstract |
A neural paraphrase generator receives a sequence of tuples comprising a source sequence of words, each tuple comprising word data element and structured tag element representing a linguistic attribute about the word data element. An RNN encoder receives a sequence of vectors representing a source sequence of words, and RNN decoder predicts a probability of a target sequence of words representing a target output sentence based on a recurrent state in the decoder. An input composition component includes a word embedding matrix and a tag embedding matrix transforms the input sequence of tuples into a sequence of vectors. An output decomposition component outputs a target sequence of tuples representing predicted words and structured tag elements, the probability of each single tuple from the output is predicted based on a recurrent state of the decoder. |
| priorityDate |
2017-05-15^^<http://www.w3.org/2001/XMLSchema#date> |
| type |
http://data.epo.org/linked-data/def/patent/Publication |