IP Library › Granted Patent US 11,790,015
Granted Patent B2
US 11,790,015 · App. 17/903,012 · Granted Oct 17, 2023

Extended query performance prediction framework utilizing passage-level information

Inventor: Haggai Roitman (Yokneam Illit, IL)
Assignee: International Business Machines Corporation
G06F16/93G06F16/90335
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,790,015
App. No.
17/903,012
Granted
Oct 17, 2023
Kind
B2
Abstract

An illustrative embodiment includes a method for post-retrieval query performance prediction using hybrid document-passage information. The method includes: obtaining a set of documents responsive to a specific query; extracting document-level information regarding respective documents within the set; extracting passage-level information regarding respective passages of documents within the set; and estimating a likelihood that the set of documents includes relevant information to the specific query using both the document-level information and the passage-level information.

Claims (12)

1. An apparatus for post-retrieval query performance prediction using hybrid document-passage information, the apparatus comprising:

a memory; and

at least one processor coupled to the memory, the processor being operative:

to obtain a set of documents of a corpus of documents responsive to a specific query;

to extract document-level information regarding respective documents within the set;

to extract passage-level information regarding respective passages of a proper subset of documents within the document corpus, based on a probability of the proper subset of documents including relevant information independent of a specific query;

to estimate a likelihood that the proper subset of documents within the document corpus set of documents includes relevant information to the specific query by using both the document-level information and the passage-level information for the proper subset of documents of the document corpus, the proper subset of documents retrieved using the document-level information, the proper subset of documents being the top-k documents relative to the specific query.

2. A computer program product comprising a non-transitory machine-readable storage medium having machine-readable program code embodied therewith, said machine-readable program code comprising machine-readable program code configured:

to obtain a set of documents of a corpus of documents responsive to a specific query;

to extract document-level information regarding respective documents within the set;

to extract passage-level information regarding respective passages of a proper subset of documents within the document corpus, based on a probability of the proper subset of documents including relevant information independent of a specific query;

to estimate a likelihood that the proper subset of documents within the document corpus set of documents includes relevant information to the specific query by using both the document-level information and the passage-level information for the proper subset of documents of the document corpus, the proper subset of documents retrieved using the document-level information, the proper subset of documents being the top-k documents relative to the specific query.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Sep 11, 2026
From: INTERNATIONAL BUSINESS MACHINES CORPORATION
To: ANTHROPIC, PBC
Reel/Frame 075991/0666 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Sep 5, 2022
From: ROITMAN, HAGGAI
To: INTERNATIONAL BUSINESS MACHINES CORPORATION
Reel/Frame 060988/0213 →
Continuity (2)
Continuation 16234537 · Dec 27, 2018
Related Publication 20220414161A1 · Dec 29, 2022