@article{Kroon_Barbiers_Odijk_van der Pas_2020, title={Detecting syntactic differences automatically using the Minimum Description Length principle}, volume={10}, url={https://clinjournal.org/clinj/article/view/109}, abstractNote={<p>In this paper we present a systematic approach to detect and rank hypotheses about possible syntactic differences for further investigation by leveraging parallel data and using the Minimum Description Length (MDL) principle. We deploy the SQS-algorithm (‘Summarising event seQuenceS’; Tatti and Vreeken 2012) – an MDL-based algorithm – to mine ‘typical’ sequences of Part of Speech (POS) tags for each language under investigation. We create a shortlist of potential syntactic differences based on the number of parallel sentences with a mismatch in pattern occurrence. We applied our method to parallel corpora of English, Dutch and Czech sentences from the Europarl v7 corpus (Koehn 2005). The approach proved useful in both retrieving POS building blocks of a language as well as pointing to meaningful syntactic differences between languages. Despite a clear sensitivity to tagging accuracy, our results and approach are promising</p>}, journal={Computational Linguistics in the Netherlands Journal}, author={Kroon, Martin and Barbiers, Sjef and Odijk, Jan and van der Pas, Stéphanie}, year={2020}, month={Dec.}, pages={109–127} }