Question answering with entailment analysis
US-2016180217-A1 · Jun 23, 2016 · US
Avoiding supporting evidence processing when evidence scoring does not affect final ranking of a candidate answer
US2016180249A1 · US · A1
| Field | Value |
|---|---|
| Publication number | US-2016180249-A1 |
| Application number | US-201514860809-A |
| Country | US |
| Kind code | A1 |
| Filing date | Sep 22, 2015 |
| Priority date | Dec 19, 2014 |
| Publication date | Jun 23, 2016 |
| Grant date | — |
How to read this patent
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
- Title
What the patent document calls the invention.
- Abstract
A short plain-language summary of the technical disclosure.
- Assignees and inventors
Who owns or filed the patent and who is credited as inventor.
- Key dates
Filing, priority, publication, and grant dates set the timeline.
- First independent claim
The legal scope of protection — read this for what is actually claimed.
- CPC / IPC classifications
Technology tags used to group this patent with similar filings.
- Citations and related patents
Prior art links and similar publications in this corpus.
Abstract
Official abstract text for this publication.
Methods to provide selective supporting evidence processing by applying a first machine learning (ML) model to a first candidate answer to generate a first confidence score that does not consider supporting evidence for the first candidate answer, determining, from a second ML model, an expected contribution of processing supporting evidence for the first candidate answer, and upon determining that the expected contribution does not exceed a specified threshold, skipping supporting evidence processing for the first candidate answer.
First claim
Opening claim text (preview).
What is claimed is: 1 . A method to provide selective supporting evidence, comprising: applying a first machine learning (ML) model to a first candidate answer to generate a first confidence score that does not consider supporting evidence for the first candidate answer; determining, from a second ML model, an expected contribution of processing supporting evidence for the first candidate answer; and upon determining that the expected contribution does not exceed a specified threshold, skipping supporting evidence processing for the first candidate answer. 2 . The method of claim 1 , wherein the second ML model specifies: (i) a weighted coefficient of processing supporting evidence for the first candidate answer, and (ii) a range of supporting evidence feature scores, wherein each supporting evidence feature score in the range of supporting evidence scores was observed during a training session. 3 . The method of claim 2 , wherein the expected contribution comprises a product of the weighted coefficient and at least one supporting evidence feature score, of the range of supporting evidence feature scores. 4 . The method of claim 1 , wherein the threshold comprises at least one of: (i) a difference between the confidence score of a second candidate answer and the confidence score of the first candidate answer, wherein the confidence score of the second candidate answer is generated by applying the first ML model to the second candidate answer, and (ii) a difference between a confidence score threshold and the first confidence score. 5 . The method of claim 1 , further comprising: upon determining that the expected contribution exceeds the specified threshold, processing supporting evidence for the first candidate answer; scoring the first candidate answer; and ranking the first candidate answer relative to a set of other candidate answers based on a respective score for each candidate answer. 6 . The method of claim 5 , further comprising: prior to processing supporting evidence for the first candidate answer, determining that the first confidence score exceeds a minimum confidence threshold. 7 . The method of claim 1 , further comprising: producing the first and second ML models during a training session.
Assignees
Inventors
Classifications
- G06N99/005Primary
Physics · mapped topic
Physics · mapped topic
- G06N20/00Primary
Machine learning · CPC title
Learning-based routing, e.g. using neural networks or artificial intelligence · CPC title
Patent family
Related publications grouped by family.
External sources
Frequently asked questions
Answers are generated from the same data shown on this page.
- What does patent US2016180249A1 cover?
- Methods to provide selective supporting evidence processing by applying a first machine learning (ML) model to a first candidate answer to generate a first confidence score that does not consider supporting evidence for the first candidate answer, determining, from a second ML model, an expected contribution of processing supporting evidence for the first candidate answer, and upon determining …
- Who is the assignee on this patent?
- IBM
- What technology area does this patent fall under?
- Primary CPC classification G06N99/005. Mapped technology areas include Physics.
- When was this patent published?
- Publication date Thu Jun 23 2016 00:00:00 GMT+0000 (Coordinated Universal Time) (A1). Legal status and post-grant events are not shown on this page.
- What related patents are in patentsdb?
- We list 3 related publications on this page (citations in our corpus or others sharing the same primary CPC).