Bruno Oberle, computational linguist and developer

Python & web developer with 5 years of experience, I have been working at a cybersecurity firm for 2 years. I have worked 3 years with machine learning techniques applied to textual data processing (NLP). I build SaaS applications in Python and JavaScript with Flask and Django, but I also have experiences with Java, C/C++, Go and Perl.

Feel free to contact me at .

See my resume and skills...

Bruno Oberle, computational linguist and developer

Projects

Natural Language Processing (NLP), programming, linguistics, but also Ancient Greek, electronics, photography... Here is a selection of my projects.

see all projects

New website! Random Items Collection: randomitems.io

Want some data to fill out your mock site or test your database setup? Find easily accessible data and facts randomly extracted from Wikipedia.

From simple lists of names or emails to tables and more complex data structures with loops and grouping. Complete html tagged texts. And pictures.

Available at randomitems.io.

read more

Coreference annotation tool (SACR)

Annotate mentions and coreference relations with a simple drag-and-drop. Support for feature annotation for each mention: part of speech, gender, number, grammatical function, etc.

read more github use it now!

Coreference databases and corpora for English and French (corefdb)

Analyse coreference in a corpus with a relational databases containing tables for coreference data (mentions, chains, relations) as well as for textual structures (tokens, sentences, paragraphs, texts). Includes linguistic annotations (part of speech, named entity, etc.).

Enriched version of the Democrat corpus for French.

read more github

Neural coreference resolution system for French (cofr)

Automatically detect mentions (including singletons) and coreference relations in a French text with this neural network adaptation of a tool originally designed of English.

read more github

Ancient Greek linguistics and grammar reference sheets

Learn Ancient Grammar with my 150 reference sheets (419 pages): morphology (declension, conjugation), phonetics, syntax, usage of tenses and moods...

read more

New! Coreference exploration and analysis website

A web site to search through coreference data in French (Democrat and Ancor corpora) and compute statistics online.

Annotate, load and analyse your own data.

Will be online soon!

Coreference chains in research articles (master thesis)

A corpus linguistic study of coreference chains in IMRaD research articles: discussing the concepts of referring expression and coreference, building the corpus (webscrapping), designing annotation guidelines, annotating the texts, analyzing the annotations.

This is one of my 2 master theses (in “French linguistics”).

read more

Tree visualization of a dependency parser (dependency2tree)

Convert the CoNLL output of dependency parsers such as StanfordNLP (English) or Talismane (French) into latex or graphviz trees.

read more github

Coreference analysis tool (CRViewer)

Compute coreference chain statistics with pie charts and bar plots.

read more gitlab

Interactive 3D geometry application

Draw geometry objects in 3D: solids, lines, vectors, planes, functions...

read more github

Regular Expression For Classe Instances (refci)

Search for patterns in list of objects, such as tokens. For example:

[pos="determiner"][pos="noun" lemma="cat"]

to look for a determiner followed by a noun with the lemma cat. This works for objets in any fields, not just for linguistic objects!

read more github

Publications

In total, 9 peer-reviewed published (written) papers and 8 communications in workshops. Among them, 6 are in English, the others in French. Here is a selection of my publications.

see all publications

French coreference for spoken and written language

Wilkens R., Oberle B., Landragin F. & Todirascu A.

Proceedings of the 12th Edition of the Language Resources and Evaluation Conference (LREC), Marseille, France (2020)

paper

Types de chaînes de référence dans les articles de recherche de format IMRaD

Oberle B.

Discours: A journal of linguistics, psycholinguistics and computational linguistics, 25 (2020)

paper

Détection automatique de chaînes de coréférence pour le français écrit: règles et ressources adaptées au repérage de phénomènes linguistiques spécifiques

Oberle B.

Actes des Rencontres des Etudiants Chercheurs en Informatique pour le Traitement Automatique des Langues (TALN-RECITAL), Association française pour l'Intelligence Artificielle, Toulouse (2019)

paper poster

Annotating with SACR and exploiting annotations (CRViewer, Excel)

Oberle B.

Workshop at Cardiff University (invited by Lise Fontaine), United Kingdom, May the 10th, 2019

slides

Chaînes de référence et structuration textuelle: quelques indicateurs...

Oberle B.

Workshop “Mesures statistiques et approches quantitatives”, LiLPa (Linguistique, Langues, Parole), UR 1339, Université de Strasbourg, 14 juin 2019, Strasbourg, France

slides

SACR: A Drag-and-Drop Based Tool for Coreference Annotation

Oberle B.

Proceedings of the 11th Edition of the Language Resources and Evaluation Conference (LREC), Miyazaki, Japan (2018)

paper poster

Les chaînes de référence dans les textes encyclopédiques du 12e au 21e siècle: étude longitudinale

Oberle B., Schnedecker C., Baumer E., Capin D., Glikman J., Guo C., Revol T., Todirascu A. & Tushkova J.

Travaux de Linguistique, 77 (2018)

paper

Les noms d'humains en -phobe

Oberle B.

In Schnedecker C. et Mihatsch W., Nouvelles approches en sémantique lexicale: les noms d'humains (théorie, méthodologie, classification). De Gruyter (2018)

paper

Photographs

Analog photography in black-and-white and color. Discover my photo lab here. Here is a selection of my photographs.

see all photographs

Corsica, 2003

Corsica, 2003

Colmar (drama), 2005

Paris (Jardin du Luxembourg), 2005

Ribeauvillé, Alsace, 2003

Corsica, 2003

Turckheim, Alsace, 2005 (color film photography)

Bretagne, 2005

Corsica, 2003

Nîmes, 2005

Avignon, Palais des Papes, 2005

Saintes-Maries-de-la-Mer, 2005

Douarnenez, Bretagne, 2005

Bretagne, 2005

Chess game, 2005

Corsica, 2003