Pablo Ruiz Fabo Email & Phone Number

Strasbourg, FR

Strasbourg Area, France

• Research on Natural Language Processing at the Linguistique, Langues, Parole lab (LiLPa)
• Teaching: Language technologies, web programming, markup languages

Madrid Area, Spain

• Research at the Digital Humanities Innovation Lab (LINHD) at Universidad Nacional de Educación a Distancia (UNED)
• NLP applications in Digital Humanities

Paris Area, France

• PhD student at the LATTICE lab (CNRS, ENS, Paris 3, PSL Research U, USPC)
• Thesis: Concept-based and Relation-based Corpus Navigation: Applications of Natural Language Processing in Digital Humanities

Bilbao Area, Spain

• Researcher position in text analytics and accessibility at an applied research center.
• Designed and developed a prototype for the lexical normalization of Spanish tweets, that applies rule-sets and language models, performing above average as per standard tests.
• Created phonological similarity databases for a sequence alignment engine used in automatic subtitling, having significantly increased the aligner’s accuracy.
• Grant application coordination at regional and state level; collaborated in applications at EU level.

• Developed internal tools for analyzing text-mining results and processes, and for obtaining information-retrieval metrics.
• Developed controlled vocabularies, extraction rules, and classifiers for clients in different verticals, for text-types such as news content, vertical-specific content and user-generated content.
• Integrated annotations obtained through text mining in a search engine that offers faceted navigation based on linguistic metadata.

Paris Area, France

• Refined machine translation resources for Spanish language pairs: terminology acquisition, lexicographical analysis, coding of morphological and syntactic information.
• Trained statistical translation models for client projects.
• Developed supplemental resources like entity extraction or a spell checking module, with a view to improving translation quality.
• Regression testing on linguistic behaviour of software for multiple languages.

Planned and taught courses in grades 6 to 10 at a secondary school within the state school-system, assessing students' performance and meeting with parents and colleagues (in German) in order to support the development of the children.

Montreal, Canada Area

• Linguistic development of rule-based and statistical components for multilingual text mining.
• Led the linguistic development of the company's Spanish sentiment-analysis module, and of a Spanish generic categorizer.
• Customized models for clients or refined generic models in English, French and Spanish. Created training corpora, trained and tested models. Customized rule-based models.
• Linguistic technologies:- Concept extraction- Entity extraction and classification- Categorization- Sentiment analysis- Summarization

Montreal, Canada Area

Designed teaching materials, such as data sets relevant to the study of specific linguistic properties, and taught weekly lessons centered around solving problem-sets, for courses like: - Phonologie et phonétique de l’espagnol (ESP3511) - Grammaire avancée (ESP2536)

Recruited participants (patients) for studies on linguistic disorders such as aphasia. Carried out psycholinguistic tests with patients. Recorded and edited stimuli for experiments, analyzed speech samples produced by participants.

Doctor Of Philosophy - Phd, Natural Language Processing And Digital Humanities

• Thesis Title: Concept-based and Relation-based Corpus Navigation: Applications of Natural Language Processing in Digital Humanities •.

M.A., Linguistics

B.A., English Philology, Spanish

1997-98: Exchange at Universität Heidelberg, Germany.