# KERMIT -- A Transformer-Based Approach for Knowledge Graph Matching

arXiv: https://arxiv.org/abs/2204.13931 · HTML: https://mlsanity.com/paper/2204.13931/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 19 references that are in the map.
- First posted on arXiv 29 Apr 2022.

## Builds on (most cited first, 6 of 6)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Supervised Ontology and Instance Matching with MELT](https://mlsanity.com/paper/2009.11102/) (2020)
- [Visual Analysis of Ontology Matching Results with the MELT Dashboard](https://mlsanity.com/paper/2004.12628/) (2020)
- [Matching with Transformers in MELT](https://mlsanity.com/paper/2109.07401/) (2021)

## Built on by (most cited first, 1 of 1)

- [OLaLa: Ontology Matching with Large Language Models](https://mlsanity.com/paper/2311.03837/) (2023)

## Abstract (arXiv)

One of the strongest signals for automated matching of knowledge graphs and ontologies are textual concept descriptions. With the rise of transformer-based language models, text comparison based on meaning (rather than lexical features) is available to researchers. However, performing pairwise comparisons of all textual descriptions of concepts in two knowledge graphs is expensive and scales quadratically (or even worse if concepts have more than one description). To overcome this problem, we follow a two-step approach: we first generate matching candidates using a pre-trained sentence transformer (so called bi-encoder). In a second step, we use fine-tuned transformer cross-encoders to generate the best candidates. We evaluate our approach on multiple datasets and show that it is feasible and produces competitive results.