Corpus ID: 237513823

Matching with Transformers in MELT

@article{Hertling2021MatchingWT,
  title={Matching with Transformers in MELT},
  author={Sven Hertling and Jan Portisch and Heiko Paulheim},
  journal={ArXiv},
  year={2021},
  volume={abs/2109.07401}
}
One of the strongest signals for automated matching of ontologies and knowledge graphs are the textual descriptions of the concepts. The methods that are typically applied (such as characteror token-based comparisons) are relatively simple, and therefore do not capture the actual meaning of the texts. With the rise of transformer-based language models, text comparison based on meaning (rather than lexical features) is possible. In this paper, we model the ontology matching task as… Expand

Figures and Tables from this paper

Fine-TOM Matcher Results for OAEI 2021
In this paper, the Fine-Tuned Transformes for Ontology matching (Fine-TOM) matching system is presented along with the results it achieved during its first participation in the Ontology AlingmentExpand
TOM Matcher Results for OAEI 2021
This paper presents the matching system TOM together with its results in the Ontology Alignment Evaluation Initiative 2021 (OAEI 2021). This is the first participation of TOM in the OAEI.Expand
ATBox results for OAEI 2020
ATBox matcher is a scalable system for instance (Abox) and schema (Tbox) matching. It uses two pipelines for generating candidates for the schema and instance matching, and utilizes the schemaExpand

References

SHOWING 1-10 OF 22 REFERENCES
Entity Matching with Transformer Architectures - A Step Forward in Data Integration
TLDR
This paper empirically compares the capability of transformer architectures and transfer-learning on the task of EM and shows that transformer architectures outperform classical deep learning methods in EM by an average margin of 27.5%. Expand
Ontology Matching
TLDR
The second edition of Ontology Matching has been thoroughly revised and updated to reflect the most recent advances in this quickly developing area, which resulted in more than 150 pages of new content. Expand
MELT - Matching EvaLuation Toolkit
TLDR
This paper presents an open source matching toolkit that integrates well into existing platforms, as well as an exemplary analysis of two OAEI 2018 tracks demonstrating advantages and analytical capabilities of MELT. Expand
The Knowledge Graph Track at OAEI - Gold Standards, Baselines, and the Golden Hammer Bias
TLDR
This paper discusses the design of the Knowledge Graph track and two different strategies of gold standard creation, and shows that all tools submitted to the track suffer from a bias which is named the golden hammer bias. Expand
Visual Analysis of Ontology Matching Results with the MELT Dashboard
TLDR
M ELT Dashboard is introduced, an interactive Web user interface for ontology alignment evaluation which is created with the existing Matching EvaLuation Toolkit (MELT), which offers detailed group evaluation capabilities that allow for the application in broad evaluation campaigns such as the Ontology Alignment Evaluation Initiative (OAEI). Expand
DAEOM: A Deep Attentional Embedding Approach for Biomedical Ontology Matching
TLDR
An alternative ontology matching framework called Deep Attentional Embedded Ontology Matching (DAEOM), which models the matching process by embedding techniques with jointly encoding ontology terminological description and network structure, and is competitive with several OAEI top-ranked systems in terms of F-measure. Expand
Supervised ontology and instance matching with MELT
TLDR
MELT-ML is presented, a machine learning extension to the Matching and EvaLuation Toolkit which facilitates the application of supervised learning for ontology and instance matching. Expand
Intermediate Training of BERT for Product Matching
TLDR
This work applies BERT to the task of product matching in e-commerce and shows that BERT is much more training data efficient than other state-of-the-art methods. Expand
Transformers: State-of-the-Art Natural Language Processing
TLDR
Transformers is an open-source library that consists of carefully engineered state-of-the art Transformer architectures under a unified API and a curated collection of pretrained models made by and available for the community. Expand
Automatically Constructing a Corpus of Sentential Paraphrases
TLDR
The creation of the recently-released Microsoft Research Paraphrase Corpus, which contains 5801 sentence pairs, each hand-labeled with a binary judgment as to whether the pair constitutes a paraphrase, is described. Expand
...
1
2
3
...