Diego A. Barriga Martínez

Siempre empujar las fronteras del conocimiento

🗺️ CDMX, México

Sep 8, 2025 09/08/25	I'm excited to share that I'm part of the Mozilla Data Collective’s groundbreaking work! 🎉
Aug 21, 2025 08/21/25	I will be at the National Congress of Linguistics talking about free software for languages spoken on México
Jul 14, 2025 07/14/25	My first entry blog
Jun 28, 2025 06/28/25	I just recieve my acceptation letter from Master's program at IIMAS, UNAM ✨😄

recent & upcoming talks

Sep 17, 2025

XVIII National Congress of Linguistics, Guanajuato University

Pyelotl: Una paquetería de Python para procesar texto de lenguas habladas en México

Code Slides

Nov 15, 2024

FLISoL, School of Engineering, UNAM

Pyelotl una biblioteca de NLP para lenguas indígenas mexicanas

Code Slides

Sep 22, 2024

PyLatam, Mazatlán, Sinaloa

Tests efectivos con pytest, o cómo escribir código dificil de fallar

Code Slides

Sep 10, 2024

Python CDMX, Wizeline

Chit Chat, representaciones fonéticas con python

Code

Oct 21, 2020

CCOSS, Guadalajara

Sobre el desarrollo de tecnologías libres para lenguas mexicana. Caso Esquite

Code Slides Video

selected publications

AmericasNLP

Py-Elotl: A Python NLP package for the languages of Mexico

Ximena Gutierrez-Vasques, Robert Pugh, Victor Mijangos, and 7 more authors

In Proceedings of the Fifth Workshop on NLP for Indigenous Languages of the Americas (AmericasNLP), May 2025

Abs Bib Html Pdf Code

This work presents Py-elotl, a suite of tools and resources in Python for processing text in several indigenous languages spoken in Mexico. These resources include parallel corpora, linguistic taggers/analyzers, and orthographic normalization tools. This work aims to develop essential resources to support language pre-processing and linguistic research, and the future creation of more complete downstream applications that could be useful for the speakers and enhance the visibility of these languages. The current version supports language groups such as Nahuatl, Otomi, Mixtec, and Huave. This project is open-source and freely available for use and collaboration

:::bibtex
@inproceedings{gutierrez-vasques-etal-2025-py,
    author = "Gutierrez-Vasques, Ximena and Pugh, Robert and Mijangos, Victor and Barriga Martínez, Diego and Aguilar, Paul and Segura, Mikel and Innes, Paola and Santillan, Javier and Montaño, Cynthia and Tyers, Francis",
    editor = "Mager, Manuel and Ebrahimi, Abteen and Pugh, Robert and Rijhwani, Shruti and Von Der Wense, Katharina and Chiruzzo, Luis and Coto-Solano, Rolando and Oncevay, Arturo",
    title = "Py-Elotl: A Python NLP package for the languages of Mexico",
    booktitle = "Proceedings of the Fifth Workshop on NLP for Indigenous Languages of the Americas (AmericasNLP)",
    month = "May",
    year = "2025",
    address = "Albuquerque, New Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.americasnlp-1.5/",
    doi = "10.18653/v1/2025.americasnlp-1.5",
    pages = "38--47",
    ISBN = "979-8-89176-236-7",
    abstract = "This work presents Py-elotl, a suite of tools and resources in Python for processing text in several indigenous languages spoken in Mexico. These resources include parallel corpora, linguistic taggers/analyzers, and orthographic normalization tools. This work aims to develop essential resources to support language pre-processing and linguistic research, and the future creation of more complete downstream applications that could be useful for the speakers and enhance the visibility of these languages. The current version supports language groups such as Nahuatl, Otomi, Mixtec, and Huave. This project is open-source and freely available for use and collaboration"
}

Automatic Interlinear Glossing for Otomí language

Diego Barriga Martínez, Victor Mijangos*, Ximena Gutierrez-Vasques*

In Proceedings of the First Workshop on Natural Language Processing for Indigenous Languages of the Americas, June 2021

Abs Bib Html Pdf Code

In linguistics, interlinear glossing is an essential procedure for analyzing the morphology of languages. This type of annotation is useful for language documentation, and it can also provide valuable data for NLP applications. We perform automatic glossing for Otomi, an under-resourced language. Our work also comprises the pre-processing and annotation of the corpus. We implement different sequential labelers. CRF models represented an efficient and good solution for our task. Two main observations emerged from our work: 1) models with a higher number of parameters (RNNs) performed worse in our low-resource scenario; and 2) the information encoded in the CRF feature function plays an important role in the prediction of labels; however, even in cases where POS tags are not available it is still possible to achieve competitive results.

:::bibtex
@inproceedings{barriga-martinez-etal-2021-automatic,
    author = "Barriga Martínez, Diego and Mijangos*, Victor and Gutierrez-Vasques*, Ximena",
    editor = "Mager, Manuel and Oncevay, Arturo and Rios, Annette and Ruiz, Ivan Vladimir Meza and Palmer, Alexis and Neubig, Graham and Kann, Katharina",
    title = "Automatic Interlinear Glossing for Otomí language",
    booktitle = "Proceedings of the First Workshop on Natural Language Processing for Indigenous Languages of the Americas",
    month = "June",
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2021.americasnlp-1.5/",
    doi = "10.18653/v1/2021.americasnlp-1.5",
    pages = "34--43",
    abstract = "In linguistics, interlinear glossing is an essential procedure for analyzing the morphology of languages. This type of annotation is useful for language documentation, and it can also provide valuable data for NLP applications. We perform automatic glossing for Otomi, an under-resourced language. Our work also comprises the pre-processing and annotation of the corpus. We implement different sequential labelers. CRF models represented an efficient and good solution for our task. Two main observations emerged from our work: 1) models with a higher number of parameters (RNNs) performed worse in our low-resource scenario; and 2) the information encoded in the CRF feature function plays an important role in the prediction of labels; however, even in cases where POS tags are not available it is still possible to achieve competitive results."
}

Diego A. Barriga Martínez

Interests 📚

Hobbies 🌱

news

recent & upcoming talks

selected publications