US 12,248,529 B2
Multi source extraction and scoring of short query answers
Preyas Dalsukhbhai Popat, Mountain View, CA (US); Gaurav Bhaskar Gite, Zurich (CH); John Blitzer, Mountain View, CA (US); Jayant Madhavan, San Francisco, CA (US); and Aliaksei Severyn, Lachen (CH)
Assigned to Google LLC, Mountain View, CA (US)
Appl. No. 18/000,152
Filed by Google LLC, Mountain View, CA (US)
PCT Filed Mar. 9, 2022, PCT No. PCT/US2022/071054
§ 371(c)(1), (2) Date Nov. 29, 2022,
PCT Pub. No. WO2023/172334, PCT Pub. Date Sep. 14, 2023.
Prior Publication US 2023/0342411 A1, Oct. 26, 2023
Int. Cl. G06F 16/957 (2019.01); G06F 16/951 (2019.01)
CPC G06F 16/957 (2019.01) [G06F 16/951 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
receiving a search query;
generating a plurality of search results based on the search query, each of the plurality of search results having a respective passage relating to the search query;
selecting a set of the respective passages,
one of the respective passages in the set being a candidate passage belonging to a top-ranked search result of the plurality of search results, and
remaining respective passages in the set being context passages belonging to lower-ranked search results of the plurality of search results;
scoring the candidate passage using the context passages to produce an accuracy score for the candidate passage, the accuracy score indicating a level of consensus between the candidate passage and the context passages; and
in response to the accuracy score being greater than a threshold, providing the candidate passage for display as a short answer in a search result page rendered by a browser window on a display.