Identifying word-senses based on linguistic variations

• US 9,946,709 B2
• Filed: 01/12/2017
• Issued: 04/17/2018
• Est. Priority Date: 02/13/2015
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Bishop, Timothy A., Boxwell, Stephen A., Brumfield, Benjamin L., Desai, Nirav P., Vernier, Stanley J.
• Primary Examiner(s): Chawan, Vijay B
• Application Number:
  US15/404,248
• Publication Number:
  US 20170139901A1
• Time in Patent Office: 460 Days
• Field of Search: 704 9, 704 10, 704257, 704 3, 707706, 707707, 707708, 707723, 707737, 707999003, 707999001, 709230, 715230
• CPC Class Codes: G06F 40/242 Dictionaries
• CPC Class Codes: G06F 40/284 Lexical analysis, e.g. tokenisation or collocates
• CPC Class Codes: G06F 40/289 Phrasal analysis, e.g. finite state techniques or chunking
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06F 40/40 Processing or translation of natural language natural language analysis G06F40/20; semantic analysis G06F40/30
• CPC Class Codes: G06Q 50/00 Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism healthcare informatics G16H
• CPC Class Codes: G16H 10/60 for patient-specific data, e.g. for electronic patient records
• CPC Class Codes: G16H 70/00 ICT specially adapted for the handling or processing of medical references
• CPC Class Codes: G16Z 99/00 Subject matter not provided for in other main groups of this subclass

Abstract

One or more words are received. A set of frequency of occurrence values of the received word(s) within a set of domain tables is determined. A domain table in the set of domain tables is associated to the received word(s), based on the set of frequency of occurrence values meeting a threshold value. A word-sense of the received word(s) is determined based on a corresponding word-sense in the associated domain table and/or corresponding domain dictionary.

Claims

1. A computer system for identifying word-senses, the computer system comprising:

one or more computer processors, one or more computer-readable storage media, and program instructions stored on the one or more of the computer-readable storage media for execution by at least one of the one or more processors, the program instructions comprising;

program instructions to generate a set of domain tables each comprising one or more arrays of aggregated statistical information corresponding to a plurality of words, one or more word-senses corresponding to the plurality of words, and temporal properties corresponding to the plurality of words, wherein the aggregated statistical information comprises a temporal frequency of occurrence value determined using an n-gram viewer;

program instructions to receive a word;

program instructions to identify the temporal frequency of occurrence value corresponding to the received word from each domain table in the set of domain tables;

program instructions to associate the received word with one or more domain tables in the set of domain tables based on the temporal frequency of occurrence value corresponding to the received word in each of the one or more domain tables meeting a threshold value; and

program instructions to identify one or more word-senses corresponding to the received word based on one or more corresponding word-senses in the associated one or more domain tables and based on one or more corresponding word-senses in a corresponding domain dictionary.

2. The computer system of claim 1, wherein the aggregated statistical information comprises frequency of usage, frequency of co-occurrence with other words, year of usage, or usage within a specific profession or domain, or context of usage.

3. The computer system of claim 1, wherein program instructions to associate the received word with one or more domain tables in the set of domain tables is further based on:

program instructions to receive an input from a user;

program instructions to identify a context value;

program instructions to receive metadata associated with the received word; and

program instructions to receive an input from a computer system.

4. The computer system of claim 1, further comprising:

program instructions to receive an additional word; and

program instructions to identify one or more word-senses corresponding to the additional word based on one or more corresponding word-senses in the associated one or more domain tables, based on the temporal frequency of occurrence value of the additional word in the domain table meeting the threshold value, and the one or more corresponding word-senses in a corresponding domain dictionary.

5. The computer system of claim 1, wherein program instructions to determine the threshold value further comprises:

program instructions to receive a set of instructions from a user; and

program instructions to receive metadata associated with the received word.

6. The computer system of claim 1, further comprising:

program instructions to identify at least two word-senses of the received word;

program instructions to assign corresponding confidence values to the at least two word-senses, wherein the corresponding confidence values are based on the temporal frequency of occurrence value of the received word within one or more domain tables in the set of domain tables associated with the received word; and

program instructions to rank the one or more word-senses based on their corresponding confidence value.

7. The computer system of claim 1, wherein the set of domain tables comprises one or more of:

medical frequency of occurrence domain table;

medical frequency of co-occurrence domain table;

veterinary frequency of occurrence domain table;

veterinary frequency of co-occurrence domain table;

temporal frequency of occurrence domain table;

colloquial word-sense domain table;

cultural word-sense domain table; and

regional word-sense domain table.

8. A computer system for identifying word-senses, the computer system comprising:

one or more computer processors, one or more computer-readable storage media, and program instructions stored on the one or more of the computer-readable storage media for execution by at least one of the one or more processors, the program instructions comprising;

program instructions to identify a frequency of occurrence value of a received word from each of a plurality of domain tables, wherein each of the plurality of domain tables comprises a frequency of occurrence value corresponding to the received word, a word-sense corresponding to the received word, and temporal properties corresponding to the received word, wherein the frequency of occurrence value is determined using an n-gram viewer;

program instructions to associate the received word with a domain table from the plurality of domain tables based on the frequency of occurrence value corresponding to the received word meeting a threshold value; and

program instructions to identify a word-sense of the received word based on the corresponding word-sense from the associated domain table.

9. The computer system of claim 8, wherein each of the plurality of domain tables comprises aggregated statistical information corresponding to the plurality of words, the aggregated statistical information comprises frequency of usage, frequency of co-occurrence with other words, year of usage, or usage within a specific profession or domain, or context of usage.

10. The computer system of claim 9, wherein program instructions to associate the received word with each of plurality of domain tables is further based on:

program instructions to receive an input from a user;

program instructions to identify a context value;

program instructions to receive metadata associated with the received word; and

program instructions to receive an input from a computer system.

11. The computer system of claim 8, further comprising:

program instructions to receive an additional word; and

program instructions to identify one or more word-senses corresponding to the additional word based on one or more corresponding word-senses in the associated domain tables, based on the frequency of occurrence value of the additional word in the domain table meeting the threshold value, and the one or more corresponding word-senses in a corresponding domain dictionary.

12. The computer system of claim 8, wherein program instructions to determine the threshold value further comprises:

program instructions to receive a set of instructions from a user; and

program instructions to receive metadata associated with the received word.

13. The computer system of claim 8, further comprising:

program instructions to determine at least two word-senses of the received word;

program instructions to assign corresponding confidence values to the at least two word-senses, wherein the corresponding confidence values are based on the frequency of occurrence of the received word within one or more domain tables of the plurality of domain tables associated with the received word; and

program instructions to rank the one or more word-senses based on their corresponding confidence value.

14. The computer system of claim 8, wherein each of the plurality of domain tables comprises one or more of:

medical frequency of occurrence domain table;

medical frequency of co-occurrence domain table;

veterinary frequency of occurrence domain table;

veterinary frequency of co-occurrence domain table;

temporal frequency of occurrence domain table;

colloquial word-sense domain table;

cultural word-sense domain table; and

regional word-sense domain table.

15. A computer system for identifying word-senses, the computer system comprising:

one or more computer processors, one or more computer-readable storage media, and program instructions stored on the one or more of the computer-readable storage media for execution by at least one of the one or more processors, the program instructions comprising;

program instructions to generate a set of domain tables each comprising one or more arrays of aggregated statistical information corresponding to a plurality of words, one or more word-senses corresponding to the plurality of words, and temporal properties corresponding to the plurality of words, wherein the aggregated statistical information of words comprises temporal frequency of occurrence of words, wherein the temporal frequency of occurrence of words comprises a frequency of usage of words and corresponding word-senses during a specific time period;

program instructions to receive a word;

program instructions to identify the temporal frequency of occurrence corresponding to the received word from each domain table in the set of domain tables;

program instructions to associate the received word with a domain table in the set of domain tables, based on the temporal frequency of occurrence of the received word corresponding to the received word in the domain table meeting a threshold value; and

program instructions to identify one or more word-senses corresponding to the received word based on one or more corresponding word-senses in the associated domain table based on the specific time period and one or more corresponding word-senses in a corresponding domain dictionary.

16. The computer system of claim 15, wherein the aggregated statistical information comprises frequency of usage, frequency of co-occurrence with other words, year of usage, or usage within a specific profession or domain, or context of usage.

17. The computer system of claim 15, wherein program instructions to associate the received word with a domain table is further based on:

program instructions to receive an input from a user;

program instructions to identify a context value;

program instructions to receive metadata associated with the received word; and

program instructions to receive an input from a computer system.

18. The computer system of claim 15, further comprising:

program instructions to receive an additional word; and

program instructions to determine one or more word-senses corresponding to the additional word based on one or more corresponding word-senses in a second domain table in the set of domain tables, based on the temporal frequency of occurrence of the additional word in the second domain table meeting the threshold value, and on the specific time period and one the one or more corresponding word-senses in a corresponding domain dictionary.

19. The computer system of claim 15, further comprising:

program instructions to identify at least two word-senses corresponding to the received word;

program instructions to assign corresponding confidence values to the at least two word-senses, wherein the corresponding confidence values are based on the frequency of occurrence of the received word within one or more domain tables in the set of domain tables associated with the received word; and

program instructions to rank the one or more word-senses based on their corresponding confidence value.

20. The computer system of claim 15, wherein the set of domain tables comprises one or more of:

medical frequency of occurrence domain table;

medical frequency of co-occurrence domain table;

veterinary frequency of occurrence domain table;

veterinary frequency of co-occurrence domain table;

temporal frequency of occurrence domain table;

colloquial word-sense domain table;

cultural word-sense domain table; and

regional word-sense domain table.