An Unsupervised Method for Weighting Finite-state Morphological Analyzers

2 code implementations • LREC 2020 • Amr Keleg, Francis Tyers, Nick Howell, Tommi Pirinen

In this paper, we have developed a method for weighting a morphological analyzer built using finite state transducers in order to disambiguate its results.

Morphological Analysis

Apertium-fin-eng--Rule-based Shallow Machine Translation for WMT 2019 Shared Task

no code implementations • WS 2019 • Tommi Pirinen

The dictionaries and rules have been developed based on the shared task data.

Machine Translation Translation

North-S\'ami to Finnish rule-based machine translation system

no code implementations • WS 2017 • Tommi Pirinen, Francis M. Tyers, Trond Trosterud, Ryan Johnson, Kevin Unhammer, Tiina Puolakainen

Machine Translation Translation

Abu-MaTran at WMT 2015 Translation Task: Morphological Segmentation and Web Crawling

no code implementations • WS 2015 • Raphael Rubino, Tommi Pirinen, Miquel Espl{\`a}-Gomis, Nikola Ljube{\v{s}}i{\'c}, Sergio Ortiz-Rojas, Vassilis Papavassiliou, Prokopis Prokopidis, Antonio Toral

Machine Translation Translation

Heuristic Hyper-minimization of Finite State Lexicons

no code implementations • LREC 2014 • Senka Drobac, Krister Lind{\'e}n, Tommi Pirinen, Miikka Silfverberg

The most noticeable reduction in size we got with a morphological transducer for Greenlandic, whose original size is on average about 15 times larger than other morphologies.

Building an Open-Source Development Infrastructure for Language Technology Projects

no code implementations • WS 2013 • Sjur N. Moshagen, Tommi Pirinen, Trond Trosterud