Dynamic faceted search on a document corpus

Patent metadata

Field	Value
Publication number	US-11003701-B2
Application number	US-201916399180-A
Country	US
Kind code	B2
Filing date	Apr 30, 2019
Priority date	Apr 30, 2019
Publication date	May 11, 2021
Grant date	May 11, 2021

Abstract

A query-focused faceted structure generation method, system, and computer program product for generating a query-focused faceted structure from a taxonomy for searching a document corpus, including augmenting taxonomy types with new instances where the instances comprise entities within a proximity of existing instances of taxonomy types in a local embedding of entities parsed from the document corpus, ranking each instance in the augmented taxonomy with respect to its type as a function of both a distance from an instance to a query in a global embedding vector space of the entities trained from the document corpus and a distance of an instance to a type in the local embedding, and ranking the taxonomy types using expanded instances in the document corpus for each type.

First claim

What is claimed is:

1. A computer-implemented query-focused faceted structure generation method for generating a query-focused faceted structure from a taxonomy for searching a document corpus, the method comprising:
augmenting taxonomy types with new instances where the instances comprise entities within a proximity of existing instances of taxonomy types in a local embedding of entities parsed from the document corpus;
ranking each instance in the augmented taxonomy with respect to its type as a function of both a distance from an instance to a query in a global embedding vector space of the entities trained from the document corpus and a distance of an instance to a type in the local embedding; and
ranking the taxonomy types using expanded instances in the document corpus for each type.

2. The method of claim 1 , presenting a dynamic structure including a faceted structure for a narrowing search of the document corpus to a user, the faceted structure being generated by selecting the ranked taxonomy types as search categories and ranked instances within each type as search facets within each category.

3. The method of claim 1 , further comprising returning the dynamic structure as a data file to a user.

4. The method of claim 2 , further comprising returning the dynamic structure as a data file to a user.

5. The method of claim 1 , further comprising ingesting the document corpus by:
extracting the terminology that includes noun words and phrases from the document corpus to:
train a type model that generates a phrase embedding of the terminology in the document corpus; and
train a topic model that generates a second phrase embedding of the terminology in the document corpus.

6. The method of claim 1 , wherein the taxonomy types are loaded and includes a graph of type and instance nodes where instances have a consistent relationship to type.

7. The method of claim 1 , embodied in a cloud-computing environment.

8. A computer program product for query-focused faceted structure generation, the computer program product comprising a computer-readable storage medium having program instructions embodied therewith for generating a query-focused faceted structure from a taxonomy for searching a document corpus, the program instructions executable by a computer to cause the computer to perform:
augmenting taxonomy types with new instances where the instances comprise entities within a proximity of existing instances of taxonomy types in a local embedding of entities parsed from the document corpus;
ranking each instance in the augmented taxonomy with respect to its type as a function of both a distance from an instance to a query in a global embedding vector space of the entities trained from the document corpus and a distance of an instance to a type in the local embedding; and
ranking the taxonomy types using expanded instances in the document corpus for each type.

9. The computer program product of claim 8 , presenting a dynamic structure including a faceted structure for a narrowing search of the document corpus to a user, the faceted structure being generated by selecting the ranked taxonomy types as search categories and ranked instances within each type as search facets within each category.

10. The computer program product of claim 8 , further comprising returning the dynamic structure as a data file to a user.

11. The computer program product of claim 9 , further comprising returning the dynamic structure as a data file to a user.

12. The computer program product of claim 8 , further comprising ingesting the document corpus by:
extracting the terminology that includes noun words and phrases from the document corpus to:
train a type model that generates a phrase embedding of the terminology in the document corpus; and
train a topic model that generates a second phrase embedding of the terminology in the document corpus.

13. The computer program product of claim 8 , wherein the taxonomy types are loaded and includes a graph of type and instance nodes where instances have a consistent relationship to type.

14. A query-focused faceted structure generation system for generating a query-focused faceted structure from a taxonomy for searching a document corpus, the system comprising:
a processor; and
a memory, the memory storing instructions to cause the processor to perform:
augmenting taxonomy types with new instances where the instances comprise entities within a proximity of existing instances of taxonomy types in a local embedding of entities parsed from the document corpus;
ranking each instance in the augmented taxonomy with respect to its type as a function of both a distance from an instance to a query in a global embedding vector space of the entities trained from the document corpus and a distance of an instance to a type in the local embedding; and
ranking the taxonomy types using expanded instances in the document corpus for each type.

15. The system of claim 14 , presenting a dynamic structure including a faceted structure for a narrowing search of the document corpus to a user, the faceted structure being generated by selecting the ranked taxonomy types as search categories and ranked instances within each type as search facets within each category.

16. The system of claim 14 , further comprising returning the dynamic structure as a data file to a user.

17. The system of claim 15 , further comprising returning the dynamic structure as a data file to a user.

18. The system of claim 14 , further comprising ingesting the document corpus by:
extracting the terminology that includes noun words and phrases from the document corpus to:
train a type model that generates a phrase embedding of the terminology in the document corpus; and
train a topic model that generates a second phrase embedding of the terminology in the document corpus.

19. The system of claim 14 , wherein the taxonomy types are loaded and includes a graph of type and instance nodes where instances have a consistent relationship to type.

20. The system of claim 14 , embodied in a cloud-computing environment.

Assignees

• IBM

Inventors

• Kong Biying
• Rajshree Nidhi
• Gliozzo Alfio Massimiliano
• Fauceglia Nicolas Rodolfo
• Farrell Robert G
• Chowdhury Md Faisal Mahbub
• Mathur Anish

Classifications

• G06F40/289

  Phrasal analysis, e.g. finite state techniques or chunking · CPC title

• G06F16/328

  Management therefor · CPC title

• G06F16/36

  Creation of semantic tools, e.g. ontology or thesauri · CPC title

• G06F16/3344 Primary

  using natural language analysis · CPC title

• G06F16/316

  Indexing structures · CPC title