read papers from OM2023

[HamedBabaei]

• Source: http://om2023.ontologymatching.org/#ap

meanwhile i will update the paper with related works that I am studying!

[HamedBabaei]

Conversational ontology alignment with ChatGPT

• I asked the authors to share the code- because I need to see the input construction details in this work!
• the work has been done on Conference track ontologies from OAEI 2022

[HamedBabaei]

Ontology Matching using Textual Class Descriptions

• the work has been doe on Common Knowledge Graphs Track ontologies from OAEI
• Implementation is available and I need to check this: https://github.com/peng-yiwen/TEXTO

[HamedBabaei]

Combining Word and Sentence Embeddings with Alignment Extension for Property Matching

• the work has been done on conference track ontologies from OAEI 2021
• the code is available here https://github.com/anonym-om/propmatcher which they have used this framework: https://github.com/anonym-om/om/tree/main

[HamedBabaei]

Truveta Mapper: A Zero-shot Ontology Alignment Framework

• the code is available here: https://github.com/sadransh/ontology-matching-framework
• they used unsupervised OM by treating it as a translation task - byT5 model has been used here with a different and interesting training strategy!

[HamedBabaei]

Exploring Large Language Models for Ontology Alignment

• GPT-3.5 + Flan-T5 investigated!
• Bio-ML track ontologies
• prompt:

Given the lists of names and hierarchical relationships associated with two concepts, your task is to determine whether
these concepts are identical or not. Consider the following:

Source Concept Names: <list of concept names>

Parent Concepts of the Source Concept: <list of concept names>

Child Concepts of the Source Concept: <list of concept names>

... (same for the target concept)

Analyze the names and the hierarchical information provided for each concept and provide a conclusion on whether these two concepts are identical or different (“Yes” or “No”) based on their associated names and hierarchical relationships.