IP Library Granted Patent US 10,275,443
Granted Patent B2
US 10,275,443 · App. 16/055,701 · Granted Apr 30, 2019

Hybrid grammatical and ungrammatical parsing

View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 10,275,443
App. No.
16/055,701
Granted
Apr 30, 2019
Kind
B2
Abstract

A system and method for processing a natural language input. The natural language input is initially processed through a strict parser, which results in an initial parse. The initial parse is evaluated to determine if it exceeds a completeness threshold. If the initial parse does not pass the completeness threshold, any open slots are filled using type based slot filling. The final parse is then output for further processing by another system, such as a search engine.

Claims (51)

1. A method of parsing a natural language input, comprising:

receiving a natural language input;

parsing the natural language input to obtain an initial parse, the initial parse having at least one open slot;

performing type based slot filling to fill a first open slot of the at least one open slot and obtain a final parse, wherein multiple entities are eligible for the first open slot, and performing the type based slot filling comprises:

selecting a single entity to fill the first open slot; and

outputting the final parse comprising at least one of:

outputting the final parse over an input/output interface, or

outputting the final parse to a search engine.

2. The method of claim 1 , further comprising:

determining a completeness of the initial parse; and

comparing the completeness of the initial parse to a threshold,

wherein performing type based slot filling comprises performing the type based slot filling in response to the initial parse not meeting the threshold.

3. The method of claim 1 , wherein the initial parse outputs at least one text field.

4. The method of claim 1 , wherein the final parse comprises the initial parse with the single entity being filled in the first open slot.

5. The method of claim 1 , wherein the single entity is selected based on the single entity being used a lowest number of time in the initial parse.

6. The method of claim 1 , wherein the single entity is selected based on the single entity being closest to an expected position of the first open slot.

7. The method of claim 1 , wherein outputting the final parse comprises outputting the final parse to the search engine.

8. A system for parsing a natural language input, comprising:

a processor;

an input/output interface; and

memory storing computer executable instructions that when implemented by the processor cause the system to perform functions comprising:

receiving a natural language input over the input/output interface;

parsing the natural language input to obtain an initial parse, the initial parse having at least one open slot;

performing type based slot filling to fill a first open slot of the at least one open slot and obtain a final parse, wherein multiple entities are eligible for the first open slot, and performing the type based slot filling comprises:

selecting a single entity to fill the first open slot; and

outputting the final parse over the input/output interface.

9. The system of claim 8 , wherein the functions further comprise:

determining a completeness of the initial parse; and

comparing the completeness of the initial parse to a threshold,

wherein performing type based slot filling comprises performing the type based slot filling in response to the initial parse not meeting the threshold.

10. The system of claim 8 , wherein the initial parse outputs at least one text field.

11. The system of claim 8 , wherein the final parse comprises the initial parse with the single entity being filled in the first open slot.

12. The system of claim 8 , wherein the single entity is selected based on the single entity being used a lowest number of time in the initial parse.

13. The system of claim 8 , wherein the single entity is selected based on the single entity being closest to an expected position of the open slot.

14. The system of claim 8 , wherein outputting the final parse comprises outputting the final parse to a search engine.

15. A method for building a query for a search engine, comprising:

receiving a text conversation;

parsing the text conversation to obtain an initial parse, the initial parse having at least one open slot;

performing type based slot filling to fill a first open slot of the at least one open slot and obtain a final parse, wherein multiple entities are eligible for the first open slot, and performing the type based slot filling comprises:

selecting a single entity to fill the first open slot, wherein the single entity is selected based upon at least one of:

a measure of a use of the single entity in the initial parse, or

a closeness of the single entity to an expected position of the first open slot; and

outputting the final parse to a search engine.

16. The method of claim 15 , further comprising:

determining a completeness of the initial parse; and

comparing the completeness of the initial parse to a threshold,

wherein performing type based slot filling comprises performing the type based slot filling in response to the initial parse not meeting the threshold.

17. The method of claim 15 , wherein the initial parse outputs at least one text field.

18. The method of claim 15 , wherein the final parse comprises the initial parse with the single entity being filled in the first open slot.

19. The method of claim 15 , wherein the single entity is selected based on the measure of the use of the single entity in the initial parse.

20. The method of claim 15 , wherein the single entity is selected based on the closeness of the single entity to the expected position of the first open slot.

Assignments (3)
PATENT SECURITY AGREEMENT (FIRST LIEN) Recorded Sep 29, 2022
From: YAHOO ASSETS LLC
To: ROYAL BANK OF CANADA, AS COLLATERAL AGENT
Reel/Frame 061571/0773 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Dec 16, 2021
From: YAHOO AD TECH LLC (FORMERLY VERIZON MEDIA INC.)
To: YAHOO ASSETS LLC
Reel/Frame 058982/0282 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 26, 2020
From: OATH INC.
To: VERIZON MEDIA INC.
Reel/Frame 054258/0635 →