Mihael Arčan

DSC_1898 (mini)I am a Postdoctoral Researcher at Insight Centre for Data Analytics @NUI Galway. I am working in the Unit for Natural Language Processing (UNLP) under the supervision of Dr Paul Buitelaar, where my main research topic focuses on terminology and ontology translation with statistical as well as neural machine translation (SMT/NMT). I defended my PhD thesis with the title: “Machine Translation of Domain-Specific Expressions within  Ontologies and Documents”.

I studied German Language at the University of Ljubljana, Slovenia, where I defended my Diploma thesis “Named Entity Recognition for German and Slovene” under the supervision of Dr Stojan Bračič and Dr Špela Vintar. In 2009 I obtained my master’s degree in Computational linguistics at the Ruhr University in Bochum, Germany. My thesis under the supervision of Prof. Dr Ralf Klabunde dealt with the extraction of semantic relations from the Slovene national corpus. After my study, I worked for Lionbridge as a developer of language technologies for Slovene, and for the Slovenian Project “Communication in Slovene”.

At Insight@NUIG (and previously in DERI) I was working on the MONNET (Multilingual Ontologies for Networked Knowledge) project, which was a European Project with the goal to provide standards and technology to facilitate multilingual access to Semantic Web knowledge resources. During my studies, I focused on the challenges on the multilinguality of the language resources within different projects.

Current Project: MixedEmotions (Past Projects: Monnet, LIDER, EuroSentiment)

Research Topics: Statistical Machine Translation, Information Extraction, Computational Linguistics, Natural Language Processing

During my PhD study, several SMT systems/demos were deployed:

  • TeTra, system for extracting and translating specific vocabulary
  • IRIS, SMT/NMT system translating from English to (less-resourced) Irish and v.v.
  • OTTO, SMT system for multilingual enhancement of ontologies
  • ASISTENT, SMT/NMT system translating between English and morphological rich South Slavic languages (Slovene, Serbian, Croatian)
  • Insight META System, SMT system accessible through an API request, supporting all official European Union languages.
  • GrumpyBot, a sequence to sequence deep learning chatbot.

My talk at “Translation Technology Terminology Conference” on Statistical Machine Translation and Terminology.

Contact Information and Other Profiles: mihael.arcan@insight-centre.org / CV / Insight Centre profile / Orcid profile / Google Scholar / LinkedIn profile