ENHANCED LOGITS FOR NATURAL LANGUAGE PROCESSING

Techniques for using enhanced logit values for classifying utterances and messages input to chatbot systems in natural language processing. A method can include a chatbot system receiving an utterance generated by a user interacting with the chatbot system and inputting the utterance into a machine-...

Full description

Saved in:
Bibliographic Details
Main Authors Hong, Yu-Heng, Vishnoi, Vishal, Hoang, Cong Duy Vu, Vu, Thanh Tien, Dharmasiri, Yakupitiyage Don Thanuja Samodhye, Parekh, Manish, Zaremoodi, Poorya, Duong, Thanh Long, Johnson, Mark Edward, Blinov, Vladislav, Xu, Ying, Jalaluddin, Elias Luqman
Format Patent
LanguageEnglish
Published 11.07.2024
Subjects
Online AccessGet full text

Cover

Loading…
Abstract Techniques for using enhanced logit values for classifying utterances and messages input to chatbot systems in natural language processing. A method can include a chatbot system receiving an utterance generated by a user interacting with the chatbot system and inputting the utterance into a machine-learning model including a series of network layers. A final network layer of the series of network layers can include a logit function. The machine-learning model can map a first probability for a resolvable class to a first logit value using the logit function. The machine-learning model can map a second probability for a unresolvable class to an enhanced logit value. The method can also include the chatbot system classifying the utterance as the resolvable class or the unresolvable class based on the first logit value and the enhanced logit value.
AbstractList Techniques for using enhanced logit values for classifying utterances and messages input to chatbot systems in natural language processing. A method can include a chatbot system receiving an utterance generated by a user interacting with the chatbot system and inputting the utterance into a machine-learning model including a series of network layers. A final network layer of the series of network layers can include a logit function. The machine-learning model can map a first probability for a resolvable class to a first logit value using the logit function. The machine-learning model can map a second probability for a unresolvable class to an enhanced logit value. The method can also include the chatbot system classifying the utterance as the resolvable class or the unresolvable class based on the first logit value and the enhanced logit value.
Author Vu, Thanh Tien
Duong, Thanh Long
Hoang, Cong Duy Vu
Dharmasiri, Yakupitiyage Don Thanuja Samodhye
Xu, Ying
Jalaluddin, Elias Luqman
Zaremoodi, Poorya
Hong, Yu-Heng
Vishnoi, Vishal
Blinov, Vladislav
Parekh, Manish
Johnson, Mark Edward
Author_xml – fullname: Hong, Yu-Heng
– fullname: Vishnoi, Vishal
– fullname: Hoang, Cong Duy Vu
– fullname: Vu, Thanh Tien
– fullname: Dharmasiri, Yakupitiyage Don Thanuja Samodhye
– fullname: Parekh, Manish
– fullname: Zaremoodi, Poorya
– fullname: Duong, Thanh Long
– fullname: Johnson, Mark Edward
– fullname: Blinov, Vladislav
– fullname: Xu, Ying
– fullname: Jalaluddin, Elias Luqman
BookMark eNrjYmDJy89L5WTQd_XzcPRzdnVR8PF39wwJVnDzD1LwcwwJDXL0UfBx9HMPdXR3VQgI8nd2DQ729HPnYWBNS8wpTuWF0twMym6uIc4euqkF-fGpxQWJyal5qSXxocFGBkYmRsZGpiaGjobGxKkCAJdTKKE
ContentType Patent
DBID EVB
DatabaseName esp@cenet
DatabaseTitleList
Database_xml – sequence: 1
  dbid: EVB
  name: esp@cenet
  url: http://worldwide.espacenet.com/singleLineSearch?locale=en_EP
  sourceTypes: Open Access Repository
DeliveryMethod fulltext_linktorsrc
Discipline Medicine
Chemistry
Sciences
Physics
ExternalDocumentID US2024232541A1
GroupedDBID EVB
ID FETCH-epo_espacenet_US2024232541A13
IEDL.DBID EVB
IngestDate Fri Jul 26 04:30:02 EDT 2024
IsOpenAccess true
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-epo_espacenet_US2024232541A13
Notes Application Number: US202418611039
OpenAccessLink https://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20240711&DB=EPODOC&CC=US&NR=2024232541A1
ParticipantIDs epo_espacenet_US2024232541A1
PublicationCentury 2000
PublicationDate 20240711
PublicationDateYYYYMMDD 2024-07-11
PublicationDate_xml – month: 07
  year: 2024
  text: 20240711
  day: 11
PublicationDecade 2020
PublicationYear 2024
RelatedCompanies Oracle International Corporation
RelatedCompanies_xml – name: Oracle International Corporation
Score 3.548523
Snippet Techniques for using enhanced logit values for classifying utterances and messages input to chatbot systems in natural language processing. A method can...
SourceID epo
SourceType Open Access Repository
SubjectTerms CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
ELECTRIC COMMUNICATION TECHNIQUE
ELECTRIC DIGITAL DATA PROCESSING
ELECTRICITY
PHYSICS
TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHICCOMMUNICATION
Title ENHANCED LOGITS FOR NATURAL LANGUAGE PROCESSING
URI https://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20240711&DB=EPODOC&locale=&CC=US&NR=2024232541A1
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1LS8NAEB5Kfd60Kj6qBJTcQk27m8chSJonUtPQJNJbSTYpCJIWE_HvO7u02lOPuwvD7MA3j53ZGYAnyhA0xogpxBgynmYkCClqKpr2XJGyJDSvRIFspIUZeZ3TeQc-t39hRJ_QH9EcERHFEO-t0Nfr_0csV9RWNoPiA7dWL35qufImOhbhiSq7Y8uLp-7UkR3HyhI5mokzdB4oUW2MlQ7QkdY5Hrz3Mf-Xst41Kv4ZHMZIr27PoVPVPThxtrPXenD8tkl59-BI1GiyBjc3OGwuYOBFIZ8q40p8lkGaSBjLSaKEwZ5IEzsKMjvwpHg2dbi2jIJLePS91AkV5GHxd-VFluwyPLqCbr2qq2uQSmYOKcpdZ0VJlrQwl7mh5-ikFKzMmZbfQH8fpdv9x3dwypf87VJV-9Btv76rezS6bfEgZPULe_OAqw
link.rule.ids 230,309,783,888,25576,76876
linkProvider European Patent Office
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1LT8JAEJ4QfOBNUYOK2kTTG8HCboFDY0qfaimEtoYbabclMTGF2Br_vrObopy4ziSb3U2-2flm5wHwSBmCZthnHTLsMf7NSBBSdNRR1aeMpCmhcSYSZH3Vjcjrgi5q8LmthRF9Qn9Ec0REFEO8l8Jeb_6DWKbIrSy6yQeK1s92qJlyxY4FPVFkc6xZs6k5NWTD0KJA9udCh84DJYqOXOkAnewBx4P1PuZ1KZvdR8U-hcMZrpeXZ1DL8iY0jO3stSYcT6ov7yYciRxNVqCwwmFxDl3Ld_lUGVPiswzCQEIuJ4kUBt2TPN13It2xpNl8anBr6TsX8GBboeF2cA_LvyMvo2B3w_1LqOfrPGuBlLJRj-K9D1iSkhVNRqt4OIjRSUlYGjM1voL2vpWu96vvoeGGE2_pvfhvN3DCVTyOqShtqJdf39ktPsBlcifu7RewX4Oe
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Apatent&rft.title=ENHANCED+LOGITS+FOR+NATURAL+LANGUAGE+PROCESSING&rft.inventor=Hong%2C+Yu-Heng&rft.inventor=Vishnoi%2C+Vishal&rft.inventor=Hoang%2C+Cong+Duy+Vu&rft.inventor=Vu%2C+Thanh+Tien&rft.inventor=Dharmasiri%2C+Yakupitiyage+Don+Thanuja+Samodhye&rft.inventor=Parekh%2C+Manish&rft.inventor=Zaremoodi%2C+Poorya&rft.inventor=Duong%2C+Thanh+Long&rft.inventor=Johnson%2C+Mark+Edward&rft.inventor=Blinov%2C+Vladislav&rft.inventor=Xu%2C+Ying&rft.inventor=Jalaluddin%2C+Elias+Luqman&rft.date=2024-07-11&rft.externalDBID=A1&rft.externalDocID=US2024232541A1