# US 2024/0005094 A1 · Hierarchical ontology matching with self-supervision

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2024/0005094 A1
- Document ID: US20240005094A1
- Status: Published application
- Kind: A1
- Application number: 17/853,310
- Filed: 2022-06-29
- Published: 2024-01-04
- Earliest claimed: 2022-06-29
- Assignees: Microsoft Technology Licensing, LLC
- Applicants: Microsoft Technology Licensing, LLC
- Inventors: Oron NIR; Inbal SAGIV; Fardau VAN NEERDEN
- Web page: https://patentgrep.com/patent/US20240005094A1

## CPC

- G06F 40/247: Thesauruses; Synonyms
- G06F 16/313: {Selection or weighting of terms for indexing}
- G06F 16/3337: {Translation of the query language, e.g. Chinese to English}
- G06F 16/3344: {using natural language analysis}
- G06F 16/36: Creation of semantic tools, e.g. ontology or thesauri
- G06F 16/367: {Ontology}
- G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

A system for ontology matching performs operations to refine a natural language processing (NLP) model that encodes terms of a first hierarchical ontology and of a second hierarchical ontology as embeddings in a vector space in which spatial proximity between the embeddings is correlated with similarity between the associated terms. The operations to refine the NLP model include performing at least a first round of triplet loss training to decrease separation between select pairs of the embeddings sampled from the different ontologies that satisfy a first hierarchical relation while increasing separation between other pairs of the embeddings that do not satisfy the first hierarchical relation. The system then determines, from the refined NLP model, a stable matching scheme that matches each term in the first hierarchical ontology with a corresponding term of the second hierarchical ontology. Responsive to receiving terms of the first hierarchical ontology from an application, the system uses the stable matching scheme to map each of the terms of the first hierarchical ontology to a corresponding term of the second hierarchical ontology and returns the set of mapped terms from the first hierarchical ontology to the application.

## Claims

### Claim 1

A processor-implemented method for mapping terms across different ontologies, the method comprising:
refining a natural language processing (NLP) model that encodes terms of a first hierarchical ontology and of a second hierarchical ontology as embeddings in a vector space in which spatial proximity between the embeddings is correlated with similarity between the associated terms, the refining including a first round of triplet loss training;
determining, from the NLP model, a stable matching scheme that matches each term in the first hierarchical ontology with a corresponding term of the second hierarchical ontology;
receiving a group of terms of the first hierarchical ontology; and
mapping, based on the stable matching scheme, each term in the group of terms of the first hierarchical ontology to its associated corresponding term of the second hierarchical ontology; and
returning the corresponding terms from the second hierarchical ontology.

### Claim 2 (depends on 1)

The processor-implemented method of claim 1, wherein determining the stable matching scheme further comprises:
constructing a bipartite graph with nodes and edges connecting respective pairs of the nodes, the nodes being the embeddings of the first hierarchical ontology and the second hierarchical ontology and each edge of the edges having an edge weight representing a similarity between respective nodes forming endpoints of the edge;
determining the stable matching scheme for the nodes in the bipartite graph.

### Claim 3 (depends on 1)

The processor-implemented method of claim 1, wherein the group of terms of the first hierarchical ontology are associated with metadata of a digital content file and wherein the corresponding terms from the second hierarchical ontology are added to the metadata of the digital content file.

### Claim 4 (depends on 1)

The method of claim 1, wherein the operations of the first round of triplet loss training decreases separation between select pairs of the embeddings sampled from different ontologies that share a like-named child node while increasing separation between other pairs of the embeddings that do not share a like-named child node.

### Claim 5 (depends on 1)

The method of claim 1, wherein performing the first round of triplet loss training includes selecting triplets from the embeddings of the NLP model that each identify an anchor node and a positive node selected from different hierarchical ontologies, the anchor node and the positive node sharing a like-named child node that is not shared with a negative node of the triplet.

### Claim 6 (depends on 1)

The method of claim 1, further comprising:
performing a second round of triplet loss training to further refine the NLP model, wherein triplets selected for the second round of triplet loss training each include an anchor node and a positive node that share a parent node within the same hierarchical ontology and further include a negative node that is selected from the same hierarchical ontology, wherein the negative node does not share a parent node with either the anchor node or the positive node.

### Claim 7 (depends on 1)

The method of claim 1, wherein determining the stable matching scheme further comprises executing a stable marriage algorithm.

### Claim 8 (depends on 2)

The method of claim 2, wherein the bipartite graph includes edges connecting each nodes of the first hierarchical ontology to one or more nodes of the second hierarchical ontology, and wherein an edge weight of each edge in the bipartite graph is determined by computing a similarity metric with respect to embeddings corresponding to nodes coupled the edge.

### Claim 9

A system comprising:
a processing system;
memory;
a natural language processing (NLP) model refinement tool stored in the memory and executable by the processing system to refine an NLP model that encodes terms of a first hierarchical ontology and of a second hierarchical ontology as embeddings in a vector space in which distances between the embeddings correlate with similarity between the associated terms, the refining of the NLP model including at least:
performing a first round of triplet loss training effective to decrease separation between select pairs of the embeddings sampled from different ontologies that satisfy a first hierarchical relation while increasing separation between other pairs of the embeddings that do not satisfy the first hierarchical relation;
a stable match identifier stored in the memory and executable by the processing system that determines a stable matching scheme for the embeddings of the refined NLP model, the stabling matching scheme being a scheme that matches each term in the first hierarchical ontology with a corresponding term of the second hierarchical ontology; and
an ontology translation engine stored in the memory and executable by the processing system to:
receive terms of the first hierarchical ontology from an application;
use the stable matching scheme to map each of the terms of the first hierarchical ontology to its associated corresponding term of the second hierarchical ontology; and
returning the corresponding terms from the second hierarchical ontology to the application.

### Claim 10 (depends on 9)

The system of claim 9, wherein the stable match identifier is further executable to:
construct a bipartite graph with nodes and edges connecting respective pairs of the nodes, the nodes being the embeddings of the first hierarchical ontology and the second hierarchical ontology and each edge of the edges having an edge weight representing a similarity between respective nodes forming endpoints of the edge; and
determine the stable matching scheme for the nodes in the bipartite graph.

### Claim 11 (depends on 9)

The system of claim 9, wherein the group of terms of the first hierarchical ontology are associated with metadata of a digital content file and wherein the corresponding terms from the second hierarchical ontology are added to the metadata of the digital content file by the application.

### Claim 12 (depends on 9)

The system of claim 9, wherein performing the first round of triplet loss training includes selecting triplets from the embeddings of the NLP model that each identify an anchor node and a positive node selected from different hierarchical ontologies, the anchor node and the positive node sharing a like-named child node that is not shared with a negative node of the triplet.

### Claim 13 (depends on 9)

The system of claim 9, wherein the actions for refining the NLP model further include:
performing a second round of triplet loss training to further refine the NLP model, wherein triplets selected for the second round of triplet loss training each include an anchor node and a positive node that share a parent node within the same hierarchical ontology and further include a negative node that is selected from the same hierarchical ontology, wherein the negative node that does not share a parent node with either the anchor node or the positive node.

### Claim 14 (depends on 10)

The system of claim 10, wherein the stable match identifier executes a stable marriage algorithm to identify the stable matching scheme.

### Claim 15 (depends on 10)

The system of claim 10, wherein the bipartite graph includes edges connecting each of the nodes of the first hierarchical ontology to one or more nodes of the second hierarchical ontology, and wherein an edge weight of each edge in the bipartite graph is determined by computing a similarity metric with respect to embeddings corresponding to nodes coupled the edge.

### Claim 16

A tangible computer-readable storage media encoding computer executable instructions for executing a computer process comprising:
refining a natural language processing (NLP) model that encodes terms of a first hierarchical ontology and of a second hierarchical ontology as embeddings in a vector space in which spatial proximity between the embeddings is correlated with similarity between the associated terms, the refining including at least a first round of triplet loss training effective to decrease separation between select pairs of the embeddings sampled from different ontologies that satisfy a first hierarchical relation while increasing separation between other pairs of the embeddings that do not satisfy the first hierarchical relation;
determining, from the refined NLP model, a stable matching scheme that matches each term in the first hierarchical ontology with a corresponding term of the second hierarchical ontology;
receiving terms of the first hierarchical ontology;
using the stable matching scheme to map each of the terms of the first hierarchical ontology its associated corresponding term of the first hierarchical ontology; and
returning the corresponding terms from the second hierarchical ontology.

### Claim 17 (depends on 16)

The tangible computer-readable storage media of claim 16, wherein determining the stable matching scheme further comprises:
constructing a bipartite graph with nodes and edges connecting respective pairs of the nodes, the nodes being the embeddings of the first hierarchical ontology and the second hierarchical ontology and each edge of the edges having an edge weight representing a similarity between respective nodes forming endpoints of the edge;
determining the stable matching scheme for the nodes in the bipartite graph.

### Claim 18 (depends on 16)

The tangible computer-readable storage media of claim 16, wherein the group of terms of the first hierarchical ontology are associated with metadata of a digital content file and wherein the corresponding terms from the second hierarchical ontology are added to the metadata of the digital content file.

### Claim 19 (depends on 16)

The tangible computer-readable storage media of claim 16, wherein the first round of triplet loss training includes selecting triplets from the embeddings of the NLP model that each identify an anchor node and a positive node selected from different hierarchical ontologies, the anchor node and the positive node sharing a like-named child node that is not shared with a negative node of the triplet.

### Claim 20 (depends on 16)

The tangible computer-readable storage media of claim 16, wherein the refining further includes performing a second round of triplet loss training that includes selecting triplets that each include an anchor node and a positive node that share a parent node within the same hierarchical ontology and further include a negative node that is selected from the same hierarchical ontology, wherein the negative node does not share a parent node with either the anchor node or the positive node.
