US 9,436,660 B2Granted

Building and maintaining information extraction rules

AssigneeInternational Business Machines Corporation

InventorsArnaldo Carreno-Fuentes, Laura Chiticariu, Eser Kandogan, Yunyao Li, Huahai Yang

Life of this patent

Estimating the term…

Loading patent…

Abstract

Methods and arrangements for managing development of information extraction rules. One or more documents are opened for extraction. An interface is provided to create a label and thereupon label a portion of the document. The created label is stored, and an extractor is developed based on the labeling. A test interface is provided for the extractor, and results of a test conducted through the test interface are displayed. The extractor is exported. In accordance with at least one embodiment, developers are presented with eased automated guidance to write extractors, which thereby reduces an overall manual effort involved in extractor development. Generally, a focused, tutorial-type environment serves as a guide based on previously developed best practices.

Claims18

Dependent claims

A method comprising:

opening one or more documents for extraction;
providing an interface to create a label and thereupon label a portion of the document;
said providing of an interface comprising providing an extraction tasks view, a text editor and an extraction plan view;
receiving at least one labeled example, wherein the at least one labeled example is labeled by a user and wherein the at least one labeled example identifies a portion of the document to extract;
receiving at least one clue label created by the user, wherein the clue label indicates a reason for extraction of the at least one labeled example;
storing the received at least one labeled example and at least one clue label in the extraction plan;
developing an extractor using the at least one labeled example and the at least one clue label;
said developing comprising conveying a predetermined structure for guiding a user and further comprising creating extraction rules based upon the at least one labeled example and the at least one clue label;
wherein the predetermined extractor structure comprises the categories of:
basic features, candidate generation, and consolidation;
providing a test interface for the extractor;
thereupon testing the extractor through the test interface;
displaying results of a test of the extractor conducted through the test interface;
permitting iteration of said steps of developing the extractor and testing the extractor;
and
exporting the extractor.

13 more elements

An apparatus comprising:

at least one processor;
and
a computer readable storage medium having computer readable program code embodied therewith and executable by the at least one processor, the computer readable program code comprising:
computer readable program code configured to open one or more documents for extraction;
computer readable program code configured to provide an interface to create a label and thereupon label a portion of the document;
the providing of an interface comprising providing an extraction tasks view, a text editor and an extraction plan view;
computer readable program code configured to receive at least one labeled example, wherein the at least one labeled example is labeled by a user and wherein the at least one labeled example identifies a portion of the document to extract;
computer readable program code configured to receive at least one clue label created by the user, wherein the clue label indicates a reason for extraction of the at least one labeled example;
computer readable program code configured to store the received at least one labeled example and at least one clue label in the extraction plan;
computer readable program code configured to develop an extractor using the at least one labeled example and the at least one clue label;
the developing comprising conveying a predetermined structure for guiding a user and further comprising creating extraction rules based upon the at least one labeled example and the at least one clue label;
wherein the predetermined structure comprises the categories of basic features, candidate generation, and consolidation;
computer readable program code configured to provide a test interface for the extractor;
computer readable program code configured to thereupon test the extractor through the test interface;
computer readable program code configured to display results of a test of the extractor conducted through the test interface;
computer readable program code configured to permit iteration of the steps of developing the extractor and testing the extractor;
and
computer readable program code configured to export the extractor.

15 more elements

A computer program product comprising:

a computer readable storage medium having computer readable program code embodied therewith, the computer readable program code comprising:
computer readable program code configured to open one or more documents for extraction;
computer readable program code configured to provide an interface to create a label and thereupon label a portion of the document;
the providing of an interface comprising providing an extraction tasks view, a text editor and an extraction plan view;
computer readable program code configured to receive at least one labeled example, wherein the at least one labeled example is labeled by a user and wherein the at least one labeled example identifies a portion of the document to extract;
computer readable program code configured to receive at least one clue label created by the user, wherein the clue label indicates a reason for extraction of the at least one labeled example;
computer readable program code configured to store the received at least one labeled example and at least one clue label in the extraction plan;
computer readable program code configured to develop an extractor using the at least one labeled example and the at least one clue label;
the developing comprising conveying a predetermined structure for guiding a user and further comprising creating extraction rules based upon the at least one labeled example and the at least one clue label;
wherein the predetermined structure comprises the categories of:
basic features, candidate generation, and consolidation;
computer readable program code configured to provide a test interface for the extractor;
computer readable program code configured to thereupon test the extractor through the test interface;
computer readable program code configured to display results of a test of the extractor conducted through the test interface;
computer readable program code configured to permit iteration of the steps of developing the extractor and testing the extractor;
and
computer readable program code configured to export the extractor.

14 more elements

Dependencies are inferred from the claim text.

Facts

Application: 13/679,349Filed 16 Nov 2012
Published: US 2014/0143661 A122 May 2014
Granted: 6 Sep 2016
Term ends: Not estimatedThe source records don’t support an estimate.

Classification7 codes

G06F 40/166
Text processing: editing, e.g. inserting or deleting
G06F 3/0482
Based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like…:…
G06F 3/0486
For the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a…:…
G06F 16/93
Details of database functions independent of the retrieved data types: document management systems

Family

US 2014/0143661 A1Pre-grant publication · published 22 May 2014
US 9,436,660 B2This patent

From the US filing history. Foreign family members aren’t listed.

Timeline

Citations

Open elsewhere

Building an agent or pulling many patents? Use the API or MCP server instead of scraping pages. Get an API key