Classifying documents according to the sentiment they convey (whether positive or negative) is an important problem in computational linguistics. There has not been much work done in this area on general techniques that can be applied effectively to multiple languages, nor have very large data sets been used in empirical studies of sentiment classifiers. We present an empirical study of the eff...

Elliptical constructions can help to avoid repetition of identical constituents during natural-language generation. From grammar books, it is not easy to extract executable rules for ellipsis—in our case in Russian. Therefore we follow a different strategy. We test the accuracy of a rule set that has been evaluated for the two Germanic languages, Dutch and German, and the two Finno-Ugric langua...

Swedish has – like other Germanic languages – flexible stress placement, which underlies morphological rules and is also based on the individual word’s origin. The achievement of the correct usage when learning Swedish is challenging. As second language learners of Swedish in the classrooms present speakers of a variety of first languages (L1s), the opportunity has been taken to have a closer l...

Luxembourgish is embedded in a multilingual context on the divide between Romance and Germanic cultures and remains one of Europe’s under-described languages. We describe our efforts in building an large vocabulary ASR system for such a “minority” language (target language: Luxembourgish) without any transcribed audio training data. Instead, acoustic models are derived from major languages (sou...

Abstract This article sketches a new analysis of the diachronic development found in many West Germanic languages from hybrid VO-OV order to rigid OV or VO order. The discussion departs discussions Struik & Van Kemenade ( 2020 / 2022 ) and Schoenmakers (to appear) on English/Dutch, which focus role object shift information structure. My interpretation their data will be based an earlier Bro...