Interactive Dialog in Natural Language Using an Ontology

Patent metadata

Field	Value
Publication number	US-2018276273-A1
Application number	US-201715467291-A
Country	US
Kind code	A1
Filing date	Mar 23, 2017
Priority date	Mar 23, 2017
Publication date	Sep 27, 2018
Grant date	—

Abstract

Methods, systems, and computer program products for carrying out interactive dialog in natural language using an ontology are provided herein. A computer-implemented method includes generating one or more domain-driven interpretations of a natural language dialogue query provided by a user via utilization of a web ontology language; determining multiple structured base queries, from among a stored collection of structured queries, that correspond to the natural language dialogue query, in view of the one or more generated domain-driven interpretations; selecting one of the multiple determined structured base queries, based on one or more items of context information pertaining to the dialogue; automatically generating a response to the selected structured base query; and outputting the generated response to the user.

First claim

What is claimed is:

1 . A computer-implemented method, comprising:
generating one or more domain-driven interpretations of a natural language dialogue query provided by a user via utilization of a web ontology language; determining multiple structured base queries, from among a stored collection of structured queries, that correspond to the natural language dialogue query, in view of the one or more generated domain-driven interpretations; selecting one of the multiple determined structured base queries, based on one or more items of context information pertaining to the dialogue; automatically generating a response to the selected structured base query; and outputting the generated response to the user; wherein the steps are carried out by at least one computing device.

2 . The computer-implemented method of claim 1 , wherein said generating one or more domain-driven interpretations of the natural language dialogue query comprises using one or more concepts of the web ontology language to relate the natural language dialogue query with one or more of the stored collection of structured queries.

3 . The computer-implemented method of claim 1 , wherein said generating one or more domain-driven interpretations of the natural language dialogue query comprises using one or more relations of the web ontology language to relate the natural language dialogue query with one or more of the stored collection of structured queries.

4 . The computer-implemented method of claim 1 , wherein said generating one or more domain-driven interpretations of the natural language dialogue query comprises using one or more properties of the web ontology language to relate the natural language dialogue query with one or more of the stored collection of structured queries.

5 . The computer-implemented method of claim 1 , wherein said generating one or more domain-driven interpretations of the natural language dialogue query comprises using one or more allowed values of the web ontology language to relate the natural language dialogue query with one or more of the stored collection of structured queries.

6 . The computer-implemented method of claim 1 , wherein said determining comprises identifying, at run-time, a sub-graph of a knowledge graph pertaining to the web ontology language, wherein the identified sub-graph is applicable for formulating a back-end query to answer the natural language dialogue query.

7 . The computer-implemented method of claim 1 , wherein the natural language dialogue query comprises one or more non-sequential utterances provided by the user.

8 . The computer-implemented method of claim 7 , wherein said determining comprises determining one or more of the structured queries that are semantically-related to the one or more non-sequential utterances, based on the one or more generated domain-driven interpretations.

9 . The computer-implemented method of claim 1 , wherein the one or more items of context information comprise interpretation context pertaining to one or more interpretations of a previous natural language dialogue query in the dialogue.

10 . A computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a device to cause the device to:
generate one or more domain-driven interpretations of a natural language dialogue query provided by a user via utilization of a web ontology language; determine multiple structured base queries, from among a stored collection of structured queries, that correspond to the natural language dialogue query, in view of the one or more generated domain-driven interpretations; select one of the multiple determined structured base queries, based on one or more items of context information pertaining to the dialogue; automatically generate a response to the selected structured base query; and output the generated response to the user.

11 . The computer program product of claim 10 , wherein said generating one or more domain-driven interpretations of the natural language dialogue query comprises (i) using one or more concepts of the web ontology language to relate the natural language dialogue query with one or more of the stored collection of structured queries, (ii) using one or more relations of the web ontology language to relate the natural language dialogue query with one or more of the stored collection of structured queries, (iii) using one or more properties of the web ontology language to relate the natural language dialogue query with one or more of the stored collection of structured queries, and (iv) using one or more allowed values of the web ontology language to relate the natural language dialogue query with one or more of the stored collection of structured queries.

12 . The computer program product of claim 10 , wherein said determining comprises identifying, at run-time, a sub-graph of a knowledge graph pertaining to the web ontology language, wherein the identified sub-graph is applicable for formulating a back-end query to answer the natural language dialogue query.

13 . The computer program product of claim 10 , wherein the natural language dialogue query comprises one or more non-sequential utterances provided by the user, and wherein said determining comprises determining one or more of the structured queries that are semantically-related to the one or more non-sequential utterances, based on the one or more generated domain-driven interpretations.

14 . The computer program product of claim 10 , wherein the one or more items of context information comprise interpretation context pertaining to one or more interpretations of a previous natural language dialogue query in the dialogue.

15 . A system comprising:
a memory; and at least one processor operably coupled to the memory and configured for:
generating one or more domain-driven interpretations of a natural language dialogue query provided by a user via utilization of a web ontology language;
determining multiple structured base queries, from among a stored collection of structured queries, that correspond to the natural language dialogue query, in view of the one or more generated domain-driven interpretations;
selecting one of the multiple determined structured base queries, based on one or more items of context information pertaining to the dialogue;
automatically generating a response to the selected structured base query; and
outputting the generated response to the user.

16 . A computer-implemented method, comprising:
generating one or more domain-driven interpretations of a first natural language dialogue query provided by a user via utilization of a web ontology language; determining multiple structured base queries, from among a stored collection of structured queries, that correspond to the first natural language dialogue query, based on the one or more generated domain-driven interpretations; selecting one of the multiple determined structured base queries that correspond to the first natural language dialogue query, based on one or more items of context information pertaining to the dialogue; automatically generating a response to the selected structured base query that corresponds to the first natural language dialogue query; outputting, to the user, the generated response to the selected structured base query that corresponds to the first natural language dialogue query; generating one or more domain-driven interpretations of a second natural language dialogue query provided by the user via utilization of a web ontology language, w

Assignees

• IBM

Inventors

• Mittal Ashish R
• Saha Diptikalyan
• Sankaranarayanan Karthik
• Sen Jaydeep

Classifications

• G06F40/30

  Semantic analysis · CPC title

• G06F16/243 Primary

  Natural language query formulation · CPC title

• G06F17/30554

  Physics · mapped topic

• G06F17/2785

  Physics · mapped topic

• G06F17/30424

  Physics · mapped topic