Proceedings of the Fourth International Workshop on Computatinal Linguistics of Uralic Languages

Abstract

PrefaceThe 4th International Workshop on Computational Linguistics for the Uralic Languages (IWCLUL) continues the annual meetings ACL SIGUR (Association of computational linguistics' special interest group for Uralic languages) after St. Petersburg (2017), Szeged (2016), and Tromsø (2015). It took place in Helsinki from 8th to 9th January, 2018 and was organized in collaboration with the NLP Research Group at the University of Helsinki.should repeat the complete info in order to let this page of the proceedings explain itself (people might not look through the other pages)This year we received a total of 20 submissions of which we accepted 15 (one of which was withdrawn by the authors) giving total of 14 high-quality papers in the final proceedings and an acceptance rate of 75 %. The accepted papers represent a variety of languages and growing resources in the Uralic landscape: Finnish, Komi-Zyrian, Udmurt, Erzya, Northern Sámi, Pite Sámi, Nganasan and Estonian; topics covered treebanks, parsing, code-switching, language generation, automatic speech recognition, morphology, and typological treatment across all Uralic languages, among others.During this year's annual meeting we also had the first election of the ACL SIGUR board after the establishment of the new SIG in Szeged in 2016. The current board was re-elected by the ACL SIGUR membership for two further years.We thank the programming committee, local organisers and participants for making annual meetings of ACL SIG for Uralic languages possible. AbstractThis paper describes the test of a dependency parsing method which is based on bidirectional LSTM feature representations and multilingual word embedding, and evaluates the results on mono-and multilingual data. The results are similar in all cases, with a slightly better results achieved using multilingual data. The languages under investigation are Komi-Zyrian and Russian. Examination of the results by relation type shows that some language specific constructions are correctly recognized even when they appear in naturally occurring code-switching data. TiivistelmäTutkimus arvioi dependenssianalyysin menetelmää, joka perustuu kaksisuuntaiseen LSTM-piirrerepresentaatioon ja monikieliseen 'word embedding' -malliin, sekä arvioi tuloksia yksi-ja monikielisissä aineistoissa. Tulokset ovat samantapaisia, mutta hieman korkeampia moni-kuin yksikielisissä aineistoissa. Tutkitut kielet ovat komisyrjääni ja venäjä. Tulosten yksityiskohtaisempi analyysi riippuvuuksien mukaan osoittaa, että tietyt kielikohtaiset suhteet on tunnistettu oikein jopa niiden esiintyessä luonnollisissa koodinvaihtoa sisältävissä lauseissa. IntroductionSpontaneous speech data of small, endangered languages most commonly contain code-switching, ad-hoc borrowings and other kinds of language contact phenomena originating from the non-target contact language(s). Consequently, spoken corpora originating from such data contain numerous utterances in which linguistic elements from at least two languages co-occur. The most usual occurrences are c...