Home Research

Photo Current physics undergrad student and former computational linguist. When I was still active in the research world, I worked in natural language processing (NLP) and computational linguistics (CL). Specifically, NLP for morphologically complex languages, computer-assisted language documentation, morphological tagging, parsing, computational phonology and computational morphology.

I still review papers in CL & NLP and might publish the odd paper once in a while. If you’re insterested in collaborating, just shoot me an email. No promises though.

BIO

Starting my physics studies in Helsinki in September 2024 🥳 In a previous life, I was an assistant professor at the Department of Linguistics at the University of British Columbia and taught in the Master of Data Science in Computational Linguistics or MDS-CL program at UBC. Until January 2020, I was a Lecturer of Language Technology at the Department of Digital Humanities at the University of Helsinki. In Helsinki, I also worked in the FoTran. Until September 2018 I was a postdoc at the Department of Linguistics at University of Colorado Boulder working in the CLEAR group. I got my PhD at the University of Helsinki in Finland, where I worked in the Helsinki Finite-State Technology research group. In October 2016, I defended my PhD thesis on morphological tagging at the Department of Modern Languages at the University of Helsinki.

Find me on

Google Scholar, GitHub, LinkedIn, OGS

Contact

My email address is of the form username@iki.fi where the username is mpsilfve.

CV

Publications

Check Google Scholar

Thesis

Morphological Disambiguation using Probabilistic Sequence Models

Software Projects

The ParserTools toolkit for building FST morphologies from human-readable specifications (particularly for Algonquian languages)

The FinnPos morphological tagging toolkit

The HFST toolkit for finite-state algebra

Past Teaching

UBC

COLX-535: Parsing for Computational Linguistics

COLX-525: Computational Morphology

COLX-581: Natural Language Processing for Low-Resource Languages

COLX-563: Unsupervised learning

DSCI-572: Supervised learning II

University of Helsinki

Introduction to Language Technology, KIK-405, fall 2018

Models and Algorithms in NLP Applications, LDA-T3105, fall 2018

Command-Line Course, KIK-LG218, fall 2018

Introduction to Deep Learning, LDA-T3114, spring 2019

Mathematics for Linguists, KIK-LG209, spring 2019

Talks

Neural Models for Word Inflection and Phonology. Invited talk at the Department of Linguistics at Indiana University, Bloomington, IN. 04/2018

Neural Models for Morphology. Invited talk at Ling Circle at the Department of Linguistics at University of Colorado, Boulder, CO. 04/2018

GRoW Your LaTeX Skills. Invited tutorial at the Graduate Research Workshop at the Department of Linguistics at University of Colorado Boulder, Boulder, CO. 09/2017.

Open-Source Optical Character Recognition. Invited tutorial at Langnet Graduate School, Turku, Finland. 05/2015.

Morphological Disambiguation using Probabilistic Sequence Models. Invited talk at Computational Semantics Seminar at University of Colorado Boulder, Boulder, CO. 01/2015.

Corpus Tools. Invited talk at Langnet Graduate School, Turku, Finland. 12/2014.

Probabilistic parsing with weighted FSTs. Invited tutorial at FSMNLP, Donostia, Spain. 07/2012.