Scoring candidate answer passages
US-9940367-B1 · Apr 10, 2018 · US
US10180964B1 · US · B1
| Field | Value |
|---|---|
| Publication number | US-10180964-B1 |
| Application number | US-201514824654-A |
| Country | US |
| Kind code | B1 |
| Filing date | Aug 12, 2015 |
| Priority date | Aug 13, 2014 |
| Publication date | Jan 15, 2019 |
| Grant date | Jan 15, 2019 |
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.
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating candidate answer passages. In one aspect, a method includes receiving a query determined to be a question query data identifying resources determined to be responsive to the query; for each resource in a top-ranked subset of the resources: identifying a plurality of passage units in the resource; applying a set of passage unit selection criterion to the passage units, each passage unit selection criterion specifying a condition for inclusion of a passage unit in a candidate answer passage, wherein a first subset of passage unit selection criteria applies to structured content and a second subset of passage unit selection criteria applies to unstructured content; and generating, from passage units that satisfy the set of passage unit selection criterion, a set of candidate answer passages.
Opening claim text (preview).
What is claimed is: 1. A method performed by data processing apparatus, the method comprising: receiving a query determined to be a question query that seeks an answer response and data identifying resources determined to be responsive to the query and ordered according to a ranking; for each resource in a top-ranked subset of the resources: identifying a plurality of passage units in the resource, each passage unit being content from the resource and being eligible for inclusion into a candidate answer passage; applying a set of passage unit selection criterion to the passage units, each passage unit selection criterion specifying a condition for inclusion of a passage unit in a candidate answer passage, wherein a first subset of passage unit selection criteria applies to structured content and a second subset of passage unit selection criteria applies to unstructured content; and generating, from passage units that satisfy the set of passage unit selection criterion, a set of candidate answer passages, each candidate answer passage being eligible to be provided as an answer passage with search results that identify the resources determined to be responsive to the query and being separate and distinct from the search results. 2. The method of claim 1 , wherein identifying a plurality of passage units in the resource comprises identifying structured content in the resource in which passage units are arranged according to one or more relational attributes. 3. The method of claim 2 , wherein generating, from passage units that satisfy the second subset of passage unit selection criterion, a set of candidate answer passages comprises: selecting, for inclusion in a candidate answer passage, only one passage unit from the unstructured content when the one passage unit immediately precedes the structured content and includes an enumerating reference; and selecting, for inclusion in the candidate answer passage, two or more passage units that include the one passage unit and one or more passage units that immediately precede the one passage unit from the unstructured content when the one passage unit immediately preceding the structured content does not include an enumerating reference. 4. The method of claim 3 , wherein generating, from passage units that satisfy the first subset of passage unit selection criterion, a set of candidate answer passages comprises: iteratively selecting, for inclusion in the candidate answer passage, passage units from the structured content such that one passage unit from each relational attribute is selected before any second passage unit from a relational attribute is selected until a termination condition is met. 5. The method of claim 4 , wherein the termination condition of the selected passage units satisfy maximum passage size. 6. The method of claim 4 , wherein the passage units that satisfy the second subset of passage unit selection criterion are sentences. 7. The method of claim 3 , wherein generating, from passage units that satisfy the first subset of passage unit selection criterion, a set of candidate answer passages comprises: selecting, from the structured content for inclusion in the candidate answer passage and when the question query requests superlatives defined by an attribute, a subset of passage units in descending ordinal rank according to the attribute. 8. The method of claim 3 , wherein generating, from passage units that satisfy the first subset of passage unit selection criterion, a set of candidate answer passages comprises: selecting, from the structured content for inclusion in the candidate answer passage and when the question query requests an attribute of a particular entity, a passage unit that includes an attribute value of the attribute of the particular entity. 9. The method of claim 1 , wherein generating, from passage units that satisfy the first subset of passage unit selection criterion, a set of candidate answer passages comprises: iteratively selecting, for inclusion in the candidate answer passage, passage units from the structured content such that one passage unit from each relational attribute is selected before any second passage unit from a relational attribute is selected until a termination condition is met. 10. The method of claim 1 , wherein generating, from passage units that satisfy the first subset of passage unit selection criterion, a set of candidate answer passages comprises: selecting, from the structured content for inclusion in the candidate answer passage and when the question query requests superlatives defined by an attribute, a subset of passage units in descending ordinal rank according to the attribute. 11. The method of claim 1 , wherein: the structured content includes enumerated key value pairs; and generating, from passage units that satisfy the first subset of passage unit selection criterion, a set of candidate answer passages comprises selecting, from the structured content for inclusion in the candidate answer passage, a subset key value pairs. 12. A system, comprising: a data processing apparatus; and a memory storage system in data communication with the data processing apparatus and storing instructions executable by the data processing apparatus and that upon such execution cause the data processing apparatus to perform operations comprising: receiving a query determined to be a question query that seeks an answer response and data identifying resources determined to be responsive to the query and ordered according to a ranking; for each resource in a top-ranked subset of the resources: identifying a plurality of passage units in the resource, each passage unit being content from the resource and being eligible for inclusion into a candidate answer passage; applying a set of passage unit selection criterion to the passage units, each passage unit selection criterion specifying a condition for inclusion of a passage unit in a candidate answer passage, wherein a first subset of passage unit selection criteria applies to structured content and a second subset of passage unit selection criteria applies to unstructured content; and generating, from passage units that satisfy the set of passage unit selection criterion, a set of candidate answer passages, each candidate answer passage being eligible to be provided as an answer passage with search results that identify the resources determined to be responsive to the query and being separate and distinct from the search results. 13. The system of claim 12 , wherein identifying a plurality of passage units in the resource comprises identifying structured content in the resource in which passage units are arranged according to one or more relational attributes. 14. The system of claim 13 , wherein generating, from passage units that satisfy the second subset of passage unit selection criterion, a set of candidate answer passages comprises: selecting, for inclusion in a candidate answer passage, only one passage unit from the unstructured content when the one passage unit immediately precedes the structured content and includes an enumerating reference; and selecting, for inclusion in the candidate answer passage, two or more passage units that include the one passage unit and one or more passage units that immediately precede the one passage unit from the unstructured content when the one passage unit immediately preceding the structured content does not include an enumerating reference. 15. The system of claim 14 , wherein generating, from passage units that satisfy the first subset of passage unit selection criterion, a set of candidate answ
Physics · mapped topic
Physics · mapped topic
Physics · mapped topic
Physics · mapped topic
Querying, e.g. by the use of web search engines · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.