US 12,670,338 B2Granted

Providing ad hoc enriched term related corpus for language support assistant services

AssigneeInternational Business Machines Corporation

InventorsJin Shi, Chih-Yuan Lin, Shu-Chih Chen, Pei-Yi Lin, Chao Yuan Huang

Life of this patent

Estimating the term…

Loading patent…

Abstract

A method, computer system, and a computer program product are provided for responding to a language input query with ad hoc enriched term data. The technique comprises extracting information relating to the language input query using a Language Support Assistance Service. The extracted information includes one or more language terms requiring further support and an associated request type. This is identified from metadata relating to the language input query. Information is provided to a Term Related Corpus Data Service that includes one or more language terms requiring further support and the identified request type and any identified sources. The Term Related Corpus Data Service returns one or more ad hoc enriched terms that are tailored to the one or more language terms requiring further support and is according to the associated request type. The Language Support Assistance Service provides a response to the language input query.

Claims19

Dependent claims

A method for providing ad hoc enriched term data, comprising:

extracting information relating to a language input query using a Language Support Assistance Service, wherein said extracted information includes one or more language terms requiring further support;
said Language Support Assistance Service further identifying from metadata relating to said language input query, an associated request type and any sources for providing language support as appropriate;
generating an Application Consuming Support Service to process metadata associated with said input query and create a list of ad-hoc enriched terms based on said metadata to create a list of enriched terms that will fit a current application context;
said Language Support Assistance Service providing to a Term Related Corpus Data Service one or more language terms requiring any further support and any extracted information as well as said associated request type and any sources identified through at least a domain of an application from metadata, wherein a Corpus includes a large database with storage designed for storing very large amounts of data;
querying a Term Related Corpus Data Service(s) to obtain a list of ad-hoc enriched terms that fit a current application context;
said Term Related Corpus Data Service returning one or more ad hoc enriched terms to said Language Support Assistance Service, wherein a metadata format enables applications which consume language support through a service provider and a term domain;
tailoring said ad hoc enriched terms to said one or more language terms requiring further support according to said associated request type, wherein said Term Related Corpus Data Service uses any identified sources to obtain other terminology from one or more contributors to provide the ad hoc enriched terms;
and
said Language Support Assistance Service providing a response to said language input query using said ad hoc enriched terms.

6 more elements

A computer system for providing ad hoc enriched term data, comprising:

one or more processors, one or more computer-readable memories and one or more computer-readable storage media;
program instructions, stored on at least one of the one or more storage media for execution by at least one of the one or more processors via at least one of the one or more memories, to extract information relating to a language input query using a Language Support Assistance Service, wherein said extracted information includes one or more language terms requiring further support;
program instructions, stored on at least one of the one or more storage media for execution by at least one of the one or more processors via at least one of the one or more memories, to identify by the said Language Support Assistance Service from metadata relating to said language input query, an associated request type and any sources for providing language support as appropriate;
program instructions, stored on at least one of the one or more storage media for execution by at least one of the one or more processors via at least one of the one or more memories, to generate an Application Consuming Support Service to process metadata associated with said input query and create a list of ad-hoc enriched terms based on said metadata to create a list of enriched terms that will fit a current application context;
program instructions, stored on at least one of the one or more storage media for execution by at least one of the one or more processors via at least one of the one or more memories, to provide from said Language Support Assistance Service to a Term Related Corpus Data Service one or more language terms requiring further support and said request type and any sources identified through at least a domain of an application from metadata, wherein a Corpus includes a large database with storage designed for storing very large amounts of data;
program instructions, stored on at least one of the one or more storage media for execution by at least one of the one or more processors via at least one of the one or more memories, to querying a Term Related Corpus Data Service(s) to obtain a list of ad-hoc enriched terms that fit a current application context;
program instructions, stored on at least one of the one or more storage media for execution by at least one of the one or more processors via at least one of the one or more memories, to return by said Term Related Corpus Data Service one or more ad hoc enriched terms to said Language Support Assistance Service, wherein a metadata format enables applications which consume language support through a service provider and a term domain;
program instructions, stored on at least one of the one or more storage media for execution by at least one of the one or more processors via at least one of the one or more memories, to tailor said ad hoc enriched terms to said one or more language terms requiring further support according to said associated request type, wherein said Term Related Corpus Data Service uses any identified sources to obtain other terminology from one or more contributors to provide the ad hoc enriched terms;
and
program instructions, stored on at least one of the one or more storage media for execution by at least one of the one or more processors via at least one of the one or more memories, to provide by said Language Support Assistance Service a response to said language input query using said ad hoc enriched terms.

7 more elements

A computer program product for providing ad hoc enriched term data, the computer program product comprising:

one or more computer readable storage media;
program instructions, stored on at least one or more storage media for execution by at least one or more processors via at least one or more memories, to extract information relating to a language input query using a Language Support Assistance Service, wherein said extracted information includes one or more language terms requiring further support;
program instructions, stored on at least one of the one or more storage media for execution by at least one of the one or more processors via at least one of the one or more memories, to identify by the said Language Support Assistance Service from metadata relating to said language input query, an associated request type and any sources for providing language support as appropriate;
program instructions, stored on at least one of the one or more storage media for execution by at least one of the one or more processors via at least one of the one or more memories, to generate an Application Consuming Support Service to process metadata associated with said input query and create a list of ad-hoc enriched terms based on said metadata to create a list of enriched terms that will fit a current application context;
program instructions, stored on at least one of the one or more storage media for execution by at least one of the one or more processors via at least one of the one or more memories, to provide from said Language Support Assistance Service to a Term Related Corpus Data Service one or more language terms requiring further support and said request type and any sources identified through at least a domain of an application from metadata, wherein a Corpus includes a large database with storage designed for storing very large amounts of data;
program instructions, stored on at least one of the one or more storage media for execution by at least one of the one or more processors via at least one of the one or more memories, to querying a Term Related Corpus Data Service(s) to obtain a list of ad-hoc enriched terms that fit a current application context;
program instructions, stored on at least one of the one or more storage media for execution by at least one of the one or more processors via at least one of the one or more memories, to return by said Term Related Corpus Data Service one or more ad hoc enriched terms to said Language Support Assistance Service, wherein a metadata format enables applications which consume language support through a service provider and a term domain;
program instructions, stored on at least one of the one or more storage media for execution by at least one of the one or more processors via at least one of the one or more memories, to tailor said ad hoc enriched terms to said one or more language terms requiring further support according to said associated request type, wherein said Term Related Corpus Data Service uses any identified sources to obtain other terminology from one or more contributors to provide the ad hoc enriched terms;
and
program instructions, stored on at least one of the one or more storage media for execution by at least one of the one or more processors via at least one of the one or more memories, to provide by said Language Support Assistance Service a response to said language input query using said ad hoc enriched terms.

7 more elements

Dependencies are inferred from the claim text.