Device and method for training a language model
US-2024346245-A1 · Oct 17, 2024 · US
US2016125751A1 · US · A1
| Field | Value |
|---|---|
| Publication number | US-2016125751-A1 |
| Application number | US-201414570491-A |
| Country | US |
| Kind code | A1 |
| Filing date | Dec 15, 2014 |
| Priority date | Nov 5, 2014 |
| Publication date | May 5, 2016 |
| Grant date | — |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
Managing answers in a question-answering environment is disclosed. Managing answers in the question-answering environment can include sorting, based on a set of answer categories for a subject matter, a first set of answers into a first answer category and a second set of answers into a second answer category. Managing answers in the question-answering environment can include determining, using the subject matter, a first category sequence including the first answer category and the second answer category, and establishing, based on the first category sequence, a first answer sequence established from a portion of the first set of answers from the first answer category and a portion of the second set of answers from the second answer category.
Opening claim text (preview).
What is claimed is: 1 - 6 . (canceled) 7 . A computer system for managing answers in a question-answering environment, the system comprising: an answer management processor configured to: sort, based on a set of answer categories for a subject matter, a first set of answers into a first answer category and a second set of answers into a second answer category; determine, using the subject matter, a first category sequence including the first answer category and the second answer category; and establish, based on the first category sequence, a first answer sequence established from a portion of the first set of answers from the first answer category and a portion of the second set of answers from the second answer category. 8 . The system of claim 7 , wherein: the answer management processor is further configured to: sort, based on the set of answer categories, a third set of answers into a third answer category; determine, using the subject matter, a second category sequence including the first answer category, the second answer category, and the third answer category; and establish, based on the second category sequence, a second answer sequence from the portion of the first set of answers from the first answer category, the portion of the second set of answers from the second answer category, and a portion of the third set of answers from the third answer category. 9 . The system of claim 7 , further comprising: a question analyzer configured to: receive, from a user, a question relating to the subject matter; analyze, using a natural language processing technique, the question; and wherein the answer management processor is further configured to: determine, based on the question analyzer analyzing the question, the set of answer categories. 10 . The system of claim 7 , further comprising: a question analyzer configured to: receive, from a user, a question relating to the subject matter; and an answer generator configured to: identify, in response to the question analyzer receiving the question, a group of answers based on the question, the group of answers including the first set of answers and the second set of answers; and wherein the answer management processor is further configured to: analyze, by a natural language processing technique, the group of answers; and determine, based on analyzing the group of answers, the set of answer categories. 11 . The system of claim 7 , further comprising: a question analyzer configured to: receive, from a user, a question; and wherein the answer management processor is further configured to: determine the subject matter using a natural language processing technique. 12 . The system of claim 7 , wherein: the answer management processor being configured to determine, using the subject matter, the first category sequence, includes being configured to: select, from a repository of category sequences, a group of category sequences corresponding to the subject matter, the group of category sequences including the first category sequence. 13 . A computer program product for managing answers in a question-answering environment, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a computer to cause the computer to perform a method comprising: sorting, based on a set of answer categories for a subject matter, a first set of answers into a first answer category and a second set of answers into a second answer category; determining, using the subject matter, a first category sequence including the first answer category and the second answer category; and establishing, based on the first category sequence, a first answer sequence established from a portion of the first set of answers from the first answer category and a portion of the second set of answers from the second answer category. 14 . The computer program product of claim 13 , wherein the method further comprises: sorting, based on the set of answer categories, a third set of answers into a third answer category; determining, using the subject matter, a second category sequence including the first answer category, the second answer category, and the third answer category; establishing, based on the second category sequence, a second answer sequence from the portion of the first set of answers from the first answer category, the portion of the second set of answers from the second answer category, and a portion of the third set of answers from the third answer category; and providing the second answer sequence. 15 . The computer program product of claim 13 , wherein the method further comprises: receiving, from a user, a question relating to the subject matter; analyzing, by a natural language processing technique, the question; and determining, based on analyzing the question, the set of answer categories. 16 . The computer program product of claim 13 , wherein the method further comprises: receiving, from a user, a question relating to the subject matter; identifying, in response to receiving the question, a group of answers based on the question, the group of answers including the first set of answers and the second set of answers; analyzing, by a natural language processing technique, the group of answers; and determining, based on analyzing the group of answers, the set of answer categories. 17 . The computer program product of claim 13 , wherein the method further comprises: receiving, from a user, a question; and determining the subject matter using a natural language processing technique configured to analyze the question. 18 . The computer program product of claim 13 , wherein: determining, using the subject matter, the first category sequence, includes: selecting, from a repository of category sequences, a group of category sequences corresponding to the subject matter, the group of category sequences including the first category sequence. 19 - 25 . (canceled)
Probabilistic graphical models, e.g. probabilistic networks · CPC title
for electronic clinical trials or questionnaires · CPC title
using information identifiers, e.g. uniform resource locators [URL] · CPC title
using ranking · CPC title
Market surveys; Market polls · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.