Identifying and replacing logically neutral phrases in natural language queries for query processing

1. A computer-based method of identifying and replacing logically neutral phrases in natural language queries, the method comprising:

receiving a natural language query;

automatically identifying one or more logically neutral and non-logically neutral anchors in the natural language query;

automatically identifying boundaries comprising one or more logically neutral phrases by detecting semantic and logical relations between verbal phrases and functional language between and adjacent to the one or more logically neutral and non-logically neutral anchors to reintroduce non-logically neutral language back into a non-logically neutral portion of the natural language query;

generating a modified natural language query by automatically removing the boundaries comprising the one or more logically neutral phrases and optionally replacing the one or more logically neutral phrases in the natural language query; and

providing the modified natural language query to a query processing system for further processing.

2. The computer-based method of claim 1 , further comprising:

identifying the logically neutral and non-logically neutral anchors by comparing nouns and pronouns included in the received natural language query to a schema annotation file.

3. The computer-based method of claim 2 , further comprising:

identifying pronouns in the received natural language query to be further considered to determine whether they are logically neutral or non-logically neutral anchors.

4. The computer-based method of claim 1 , wherein automatically removing the boundaries comprising the one or more logically neutral phrases and optionally replacing the one or more logically neutral phrases in the natural language query further comprises:

replacing the removed boundaries including the one or more logically neutral phrases with a word that transforms a remaining portion of the received natural language query into a question.

5. The computer-based method of claim 1 , wherein detecting the semantic and logical relations between verbal phrases and functional language between and adjacent to the one or more logically neutral and non-logically neutral anchors further comprises:

detecting the semantic and logical relations between the verbal phrases and the functional language in the boundaries of the one or more logically neutral phrases based on a score-based probability extracted from a corpus.

6. The computer-based method of claim 1 , wherein detecting the semantic and logical relations between verbal phrases and functional language between and adjacent to the one or more non-logically neutral anchors further comprises:

determining the semantic and logical relations between the verbal phrases and the functional language in the boundaries of the one or more logically neutral phrases based on a score-based probability extracted from machine learning.

7. The computer-based method of claim 1 , further comprising:

using the query processing system to further modify the modified natural language query into a logical form suitable for transforming the modified natural language query into structured query language (SQL).

8. A computer system, the computer system comprising:

one or more processors, one or more computer-readable memories, one or more computer-readable tangible storage medium, and program instructions stored on at least one of the one or more computer-readable tangible storage medium for execution by at least one of the one or more processors via at least one of the one or more computer-readable memories, wherein the computer system is capable of performing a method comprising:

receiving a natural language query;

automatically identifying one or more logically neutral and non-logically neutral anchors in the natural language query;

automatically identifying boundaries comprising one or more logically neutral phrases by detecting semantic and logical relations between verbal phrases and functional language between and adjacent to the one or more logically neutral and non-logically neutral anchors to reintroduce non-logically neutral language back into a non-logically neutral portion of the natural language query;

generating a modified natural language query by automatically removing the boundaries comprising the one or more logically neutral phrases and optionally replacing the one or more logically neutral phrases in the natural language query; and

providing the modified natural language query to a query processing system for further processing.

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

identifying the logically neutral and non-logically neutral anchors by comparing nouns and pronouns included in the received natural language query to a schema annotation file.

10. The computer system of claim 9 , further comprising:

identifying pronouns in the received natural language query to be further considered to determine whether they are logically neutral or non-logically neutral anchors.

11. The computer system of claim 10 , wherein automatically removing the boundaries comprising the one or more logically neutral phrases and optionally replacing the one or more logically neutral phrases in the natural language query further comprises:

replacing the removed boundaries including the one or more logically neutral phrases with a word that transforms a remaining portion of the received natural language query into a question.

12. The computer system of claim 8 , wherein detecting the semantic and logical relations between verbal phrases and functional language between and adjacent to the one or more logically neutral and non-logically neutral anchors further comprises:

detecting the semantic and logical relations between the verbal phrases and the functional language in the boundaries of the one or more logically neutral phrases based on a score-based probability extracted from a corpus.

13. The computer system of claim 8 , wherein detecting the semantic and logical relations between verbal phrases and functional language between and adjacent to the one or more non-logically neutral anchors further comprises:

determining the semantic and logical relations between the verbal phrases and the functional language in the boundaries of the one or more logically neutral phrases based on a score-based probability extracted from machine learning.

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

using the query processing system to further modify the modified natural language query into a logical form suitable for transforming the modified natural language query into structured query language (SQL).

15. A computer program product, the computer program product comprising:

one or more computer-readable tangible storage medium and program instructions stored on at least one of the one or more computer-readable tangible storage medium, the program instructions executable by a processor capable of performing a method, the method comprising:

receiving a natural language query;

automatically identifying one or more logically neutral and non-logically neutral anchors in the natural language query;

automatically identifying boundaries comprising one or more logically neutral phrases by detecting semantic and logical relations between verbal phrases and functional language between and adjacent to the one or more logically neutral and non-logically neutral anchors to reintroduce non-logically neutral language back into a non-logically neutral portion of the natural language query;

generating a modified natural language query by automatically removing the boundaries comprising the one or more logically neutral phrases and optionally replacing the one or more logically neutral phrases in the natural language query; and

providing the modified natural language query to a query processing system for further processing.

16. The computer program product of claim 15 , further comprising:

identifying the logically neutral and non-logically neutral anchors by comparing nouns and pronouns included in the received natural language query to a schema annotation file.

17. The computer program product of claim 15 , further comprising:

identifying pronouns in the received natural language query to be further considered to determine whether they are logically neutral or non-logically neutral anchors.

18. The computer program product of claim 16 , wherein automatically removing the boundaries comprising the one or more logically neutral phrases and optionally replacing the one or more logically neutral phrases in the natural language query further comprises:

replacing the removed boundaries including the one or more logically neutral phrases with a word that transforms a remaining portion of the received natural language query into a question.

19. The computer program product of claim 15 , wherein detecting the semantic and logical relations between verbal phrases and functional language between and adjacent to the one or more logically neutral and non-logically neutral anchors further comprises:

detecting the semantic and logical relations between the verbal phrases and the functional language in the boundaries of the one or more logically neutral phrases based on a score-based probability extracted from a corpus.

20. The computer program product of claim 15 , further comprising using the query processing system to further modify the modified natural language query into a logical form suitable for transforming the modified natural language query into structured query language (SQL).