Determining off-topic questions in a question answering system using probabilistic language models
US10713438B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Jun 15, 2016 |
| Grant date | Jul 14, 2020 |
| Priority date | — |
| Expiry date | Mar 11, 2039 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N5/045
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A question answering system that determines whether a question is off-topic by performing the following steps: (i) receiving, by a question answering system, a set of documents; (ii) identifying topical subset(s) for each document of the set of documents using named entity recognition, where each topical subset relates to a corresponding topic; (iii) assigning a set of topic score(s) for each topical subset using natural language processing, where each topic score relates to a corresponding probability associated with the respective topical subset under a probabilistic language model; and (iv) determining, based, at least in part, on the topic score(s) corresponding to the topical subset(s), whether a question input into the question answering system is off-topic.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.