Skip to main content

Matcha-DL is a tool for supervised ontology alignment. It takes as input two ontologies and a set of mappings between them, and learns a model that can predict mappings between the two ontologies.

Project description

Matcha DL

Description

Matcha-DL is an extension of the matching system Matcha to tackle semi-supervised tasks using machine-learning algorithms. Matcha builds upon the algorithms of the established system AgreementMakerLight with a novel broader core architecture designed to tackle long-standing challenges such as complex and holistic ontology matching. Matcha-DL uses a linear neural network that learns to rank candidate mappings proposed by Matcha by using a partial reference alignment as a training set, and using the confidence scores produced by Matcha's matching algorithms as features.

Installation

To install Matcha DL, you can use pip:

pip install matcha-dl

USAGE

CLI

Matcha DL provides a command line interface for computing the alignment between two ontologies. Here's how you can use it:

matchadl --source_ontology_file <source_file_path> --target_ontology_file <target_file_path> --output_dir <output_dir_path> [--reference_file <reference_file_path>] [--candidates_file <candidates_file_path>] [--config_file <config_file_path>]

API

AlignmentRunner Class

The AlignmentRunner is a quick and easy class that can be programaticly imported to run an alignemnt using Matcha-DL.

Here's an example on how to use it:

from matcha_dl import AlignmentRunner

runner = AlignmentRunner(
    source_ontology_file="path/to/source_ontology_file",
    target_ontology_file="path/to/target_ontology_file",
    output_dir="path/to/output_dir",
    reference_file="path/to/reference_file",
    candidates_file="path/to/candidates_file",
    config_file="path/to/config_file"
)

runner.run()

Arguments

  • --source_ontology_file or -s: Path to the source ontology file (required)
  • --target_ontology_file or -t: Path to the target ontology file (required)
  • --output_dir or -o: Path to the output directory (required)
  • --reference_file or -r: Path to the reference file (optional)
  • --candidates_file or -c: Path to the candidates file (optional)
  • --config_file or -C: Path to the config file (optional)

Details

Tasks

Supervised/Unsupervised settings

If reference files are provided Matcha-DL will train a model to predict an alignment, otherwise it will use the scores from matcha to compute the alignment directly.

Global Alignment/ Local Alignment

If a candidates file is provided Matcha-DL will generate a ranking for those candidates (local alignment), otherwise it will perform global pairwise alignemnt for all the entities in the source and target ontologies.

Acknowledgements

This work was supported by FCT through the fellowships 2022.10557.BD (Pedro Cotovio) and 2022.11895.BD (Marta Silva), and through the LASIGE Research Unit, ref. UIDB/00408/2020 (https://doi.org/10.54499/UIDB/00408/2020) and ref. UIDP/00408/2020 (https://doi.org/10.54499/UIDP/00408/2020). It was also partially supported by the KATY project which has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement No 101017453. This work was also supported partially by project 41, HfPT: Health from Portugal, funded by the Portuguese Plano de Recuperação e Resiliência.

Contributions

Authors:

Pedro Giesteira Cotovio, [1], Lucas Ferraz, [1], Daniel Faria, [2], Laura Balbi, [1], Marta Contreiras Silva, [1], Catia Pesquita, [1]

Institutions:

  1. LASIGE, Faculdade de Ciências, Universidade de Lisboa, Portugal
  2. INESC-ID, Instituto Superior Técnico, Universidade de Lisboa, Portugal

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

matcha_dl-0.1.1.tar.gz (22.8 kB view details)

Uploaded Source

Built Distribution

matcha_dl-0.1.1-py3-none-any.whl (29.7 kB view details)

Uploaded Python 3

File details

Details for the file matcha_dl-0.1.1.tar.gz.

File metadata

  • Download URL: matcha_dl-0.1.1.tar.gz
  • Upload date:
  • Size: 22.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.8.2 CPython/3.10.12 Linux/5.15.0-105-generic

File hashes

Hashes for matcha_dl-0.1.1.tar.gz
Algorithm Hash digest
SHA256 4e37c613d8cfed54f71a9c1933451df633f8af2f6aa9b107e48fd507eeb64a92
MD5 3d9f6adce1075305ff5cec97b35cf02e
BLAKE2b-256 79503389dbc6c5630daae27277b170367a42844d555e71e89b934b08ceca7ae1

See more details on using hashes here.

File details

Details for the file matcha_dl-0.1.1-py3-none-any.whl.

File metadata

  • Download URL: matcha_dl-0.1.1-py3-none-any.whl
  • Upload date:
  • Size: 29.7 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.8.2 CPython/3.10.12 Linux/5.15.0-105-generic

File hashes

Hashes for matcha_dl-0.1.1-py3-none-any.whl
Algorithm Hash digest
SHA256 15a5bdcb44295d903915c6188cead8ab787d67279f754362d29765f80e262140
MD5 5f5e6185925f91f6c5826cf967a828d2
BLAKE2b-256 1a7fa178ad0009e81029cca2df42661d8fd150574006240772c4045b4111aab3

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page