Providing a semantic encoding and language neural network

Patent metadata

Field	Value
Publication number	US-2024013003-A1
Application number	US-202217811763-A
Country	US
Kind code	A1
Filing date	Jul 11, 2022
Priority date	Jul 11, 2022
Publication date	Jan 11, 2024
Grant date	—

Abstract

Embodiments are provided for unsupervised learning of domain specific knowledge graph from textual data and language generation from knowledge graph via reinforcement learning in a computing system by a processor. Unstructured data is automatically parsed into one or more knowledge graphs based on the unstructured data and a list of candidate relations using a first machine learning model. Text data is generated from the one or more knowledge graphs using a second machine learning model.

First claim

1 . A method for providing semantic encoding and language generation in a computing system by a processor, comprising:
automatically parsing unstructured data into one or more knowledge graphs based on the unstructured data and a list of candidate relations using a first machine learning model; and generating text data from the one or more knowledge graphs using a second machine learning model.

2 . The method of claim 1 , further including training the first machine learning model and the second machine learning model using the unstructured data and a list of candidate relations via unsupervised machine learning using the unstructured data and the list of candidate relations, wherein the first machine learning model is a semantic encoder and the second machine learning model is a semantic decoder.

3 . The method of claim 1 , further including using the first machine learning model to:
identify the plurality of entities in the unstructured data; and encode the unstructured data into a distribution of a plurality of triples in the one or more knowledge graphs.

4 . The method of claim 1 , further including using the second machine learning model to:
identify a set of the plurality of triples of the one or more knowledge graphs; and decode the set of the plurality of triples into the text data, wherein a triple includes a subject, object, and predicate in the unstructured data, wherein the subject and object are an entity and a predicate is a relation.

5 . The method of claim 1 , further including sampling a set of the plurality of triples from the unstructured data of one or more knowledge graphs for training a plurality of machine learning models via unsupervised machine learning.

6 . The method of claim 5 , further including:
generating text data from the set of the plurality of triples applying using the second machine learning model; and assigning a penalty score to the set of the plurality of triples based on a degree of differences between the unstructured data and the text data.

7 . The method of claim 1 , further including:
identifying one or more candidate entities in the unstructured data; and using the one or more candidate entities as nodes in the one or more knowledge graphs.

8 . A system for providing semantic encoding and language generation in a computing environment, comprising:
one or more computers with executable instructions that when executed cause the system to:
automatically parse unstructured data into one or more knowledge graphs based on the unstructured data and a list of candidate relations using a first machine learning model; and
generate text data from the one or more knowledge graphs using a second machine learning model.

9 . The system of claim 8 , wherein the executable instructions when executed cause the system to train the first machine learning model and the second machine learning model using the unstructured data and a list of candidate relations via unsupervised machine learning using the unstructured data and the list of candidate relations, wherein the first machine learning model is a semantic encoder and the second machine learning model is a semantic decoder.

10 . The system of claim 8 , wherein the executable instructions when executed cause the system to use the first machine learning model to:
identify the plurality of entities in the unstructured data; and encode the unstructured data into a distribution of a plurality of triples in the one or more knowledge graphs.

11 . The system of claim 8 , wherein the executable instructions when executed cause the system to use the second machine learning model to:
identify a set of the plurality of triples of the one or more knowledge graphs; and decode the set of the plurality of triples into the text data, wherein a triple includes a subject, object, and predicate in the unstructured data, wherein the subject and object are an entity and a predicate is a relation.

12 . The system of claim 8 , wherein the executable instructions when executed cause the system to sample a set of the plurality of triples from the unstructured data of one or more knowledge graphs for training a plurality of machine learning models via unsupervised machine learning.

13 . The system of claim 12 , wherein the executable instructions when executed cause the system to:
generate text data from the set of the plurality of triples applying using the second machine learning model; and assign a penalty score to the set of the plurality of triples based on a degree of differences between the unstructured data and the text data.

14 . The system of claim 8 , wherein the executable instructions when executed cause the system to:
identify one or more candidate entities in the unstructured data; and use the one or more candidate entities as nodes in the one or more knowledge graphs.

15 . A computer program product for providing semantic encoding and language generation in a computing environment, the computer program product comprising:
one or more computer readable storage media, and program instructions collectively stored on the one or more computer readable storage media, the program instruction comprising:
program instructions to automatically parse unstructured data into one or more knowledge graphs based on the unstructured data and a list of candidate relations using a first machine learning model; and
program instructions to generate text data from the one or more knowledge graphs using a second machine learning model.

16 . The computer program product of claim 15 , further including program instructions to train the first machine learning model and the second machine learning model using the unstructured data and a list of candidate relations via unsupervised machine learning using the unstructured data and the list of candidate relations, wherein the first machine learning model is a semantic encoder and the second machine learning model is a semantic decoder.

17 . The computer program product of claim 15 , further including program instructions to use the first machine learning model to:
identify the plurality of entities in the unstructured data; and encode the unstructured data into a distribution of a plurality of triples in the one or more knowledge graphs.

18 . The computer program product of claim 15 , further including program instructions to use the second machine learning model to:
identify a set of the plurality of triples of the one or more knowledge graphs; and decode the set of the plurality of triples into the text data, wherein a triple includes a subject, object, and predicate in the unstructured data, wherein the subject and object are an entity and a predicate is a relation.

19 . The computer program product of claim 15 , further including program instructions to:
sample a set of the plurality of triples from the unstructured data of one or more knowledge graphs for training a plurality of machine learning models via unsupervised machine learning; and generate text data from the set of the plurality of triples applying using the second machine learning model; and assign a penalty score to the set of the plurality of triples based on a degree of differences between the unstructured data and the text data.

20 . The computer program product of claim 15 , further including program instructions to:
identify one or more candidate entities in the unstructured data; and use the one or more candidate entities as nodes in the one or more knowledge graphs.

Assignees

• IBM

Inventors

• Hoang Thanh Lam
• Phan Dzung
• Picco Gabriele
• Nguyen Lam
• Sbodio Marco Luca
• Lopez Garcia Vanessa

Classifications

• G06F40/30 Primary

  Semantic analysis · CPC title

• G06N3/08

  Learning methods · CPC title

• G06N3/0454

  Physics · mapped topic

• G06F40/205

  Parsing · CPC title

• G06F40/279

  Recognition of textual entities · CPC title