Method and device for extracting causal from natural language sentences for intelligent systems

Patent metadata

Field	Value
Publication number	US-10528669-B2
Application number	US-201815937629-A
Country	US
Kind code	B2
Filing date	Mar 27, 2018
Priority date	Mar 20, 2018
Publication date	Jan 7, 2020
Grant date	Jan 7, 2020

Abstract

A method and device for extracting causal from natural language sentences is disclosed. The method includes determining, by a computing device, a plurality of parameters for each target word in a sentence inputted by a user. The method further includes processing for each target word, by the computing device, an input vector comprising the plurality of parameters for a causal classifier neural network. The method includes identifying, by the computing device, causal tags associated with each target word in the sentence based on processing of associated input vector. The method includes extracting, by the computing device, the causal text from the sentence based on the causal tags associated with each target word in the sentence. The method further includes providing, by the computing device, a response to the sentence inputted by the user based on the causal text extracted for the sentence.

First claim

What is claimed is:

1. A method for extracting causal from natural language sentences, the method comprising:
determining, by a computing device, a plurality of parameters for each target word in a sentence inputted by a user wherein the plurality of parameters for a target word comprise a Part of Speech (POS) vector associated with the target word comprising a POS tag for the target word and a POS tag for at least two words preceding the target word, a word embedding for the target word, a word embedding for a head word of the target word, and a dependency label for the target word;
processing for each target word, by the computing device, an input vector comprising the plurality of parameters for a causal classifier neural network;
identifying, by the computing device, causal tags associated with each target word in the sentence based on processing of associated input vector;
extracting, by the computing device, the causal text from the sentence based on the causal tags associated with each target word in the sentence; and
providing, by the computing device, a response to the sentence inputted by the user based on the causal text extracted for the sentence.

2. The method of claim 1 , wherein the dependency label for the target word indicates relation of the target with the head word in the sentence.

3. The method of claim 1 further comprising training the causal classifier neural network to identify causal tags associated with words within sentences inputted by user.

4. The method of claim 1 , wherein the sentence is inputted by the user as at least one of a verbal input and a textual input.

5. The method of claim 4 , wherein the sentence comprises a query asked by the user.

6. The method of claim 5 , wherein the response comprises at least one an answer to the query and an action corresponding to the query.

7. The method of claim 1 , wherein the causal tags comprise Begin Causal tag, Inside Causal tag, and Others tag.

8. The method of claim 7 , wherein the identifying the causal tags associated with each target word comprises:
assigning a Begin Causal tag to a word in the sentence marking the beginning of the causal text;
assigning an Inside Causal tag to each word in the causal text succeeding the word marking the beginning of the causal text; and
assigning an Others tag to each remaining word in the sentence.

9. A computing device for extracting causal from natural language sentences, the device comprising:
a processor; and
a memory communicatively coupled to the processor, wherein the memory stores processor instructions, which, on execution, causes the processor to:
determine a plurality of parameters for each target word in a sentence inputted by a user wherein the plurality of parameters for a target word comprise a Part of Speech (POS) vector associated with the target word comprising a POS tag for the target word and a POS tag for at least two words preceding the target word, a word embedding for the target word, a word embedding for a head word of the target word, and a dependency label for the target word;
process for each target word an input vector comprising the plurality of parameters for a causal classifier neural network;
identify causal tags associated with each target word in the sentence based on processing of associated input vector;
extract the causal text from the sentence based on the causal tags associated with each target word in the sentence; and
provide a response to the sentence inputted by the user based on the causal text extracted for the sentence.

10. The computing device of claim 9 , wherein the dependency label for the target word indicates relation of the target with the head word in the sentence.

11. The computing device of claim 9 , wherein the processor instructions further cause the processor to train the causal classifier neural network to identify causal tags associated with words within sentences inputted by user.

12. The computing device of claim 9 , wherein the sentence is inputted by the user as at least one of a verbal input and a textual input.

13. The computing device of claim 12 , wherein the sentence comprises a query asked by the user, and wherein the response comprises at least one an answer to the query and an action corresponding to the query.

14. The computing device of claim 9 , wherein the causal tags comprise Begin Causal tag, Inside Causal tag, and Others tag.

15. The computing device of claim 9 , wherein to identify the causal tags associated with each target word, the processor instructions further cause the processor to:
assign a Begin Causal tag to a word in the sentence marking the beginning of the causal text;
assign an Inside Causal tag to each word in the causal text succeeding the word marking the beginning of the causal text; and
assign an Others tag to each remaining word in the sentence.

16. A non-transitory computer-readable storage medium having stored thereon, a set of computer-executable instructions causing a computer comprising one or more processors to perform steps comprising:
determining a plurality of parameters for each target word in a sentence inputted by a user wherein the plurality of parameters for a target word comprise a Part of Speech (POS) vector associated with the target word comprising a POS tag for the target word and a POS tag for at least two words preceding the target word, a word embedding for the target word, a word embedding for a head word of the target word, and a dependency label for the target word;
processing for each target word an input vector comprising the plurality of parameters for a causal classifier neural network;
identifying causal tags associated with each target word in the sentence based on processing of associated input vector;
extracting the causal text from the sentence based on the causal tags associated with each target word in the sentence; and
providing a response to the sentence inputted by the user based on the causal text extracted for the sentence.

Assignees

• Wipro Ltd

Inventors

• Chatterjee Arindam
• Ballal Kartik Subodh

Classifications

• G06F40/268 Primary

  Morphological analysis · CPC title

• G06F40/30 Primary

  Semantic analysis · CPC title

• G10L25/30

  using neural networks · CPC title

• G06F40/253

  Grammatical analysis; Style critique · CPC title

• G06F40/289

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