The Department of Language Science and Technology was established in 2016, bringing together the  former departments of "Computational Linguistics and Phonetics" and "Applied Linguistics, Translation and Interpreting".

Our research and teaching span many areas of language science and technology, including computational linguistics, psycholinguistics, speech science and technology, language technology, corpus linguistics, and translation science and technology.

The department has a long tradition of joint research and teaching with Computer Science, Cognitive Psychology, and the Philologies at Saarland University and collaborates with many other institutions both nationally and internationally.


Three new LSV publications

Two papers by the LSV group were accepted to this year's "ACL 2018 Workshop on Deep Learning Approaches for Low Resource Natural Language Processing (DeepLo)". Michael Hedderich and Dietrich Klakow present a method to train a neural network in a low-resource setting by using automatically annotated data and handling the noise in the labels. Clayton Greenberg, Mittul Singh and Dietrich Klakow explore the quality of embeddings of rare words, finding that below a certain number of occurrences, SWORDSS (developed at LSV in 2016) can generate better embeddings than standard word2vec.

A paper by Marc Schulder and Michael Wiegand of the LSV group and their colleague Josef Ruppenhofer from the Institute for German Language, Mannheim, was accepted at 27th International Conference on Computational Linguistics (COLING 2018). In the paper, the authors present methods for automatically identifying verbs that, like negation, can change the sentiment polarity of a phrase (e.g. "abandon hope" or "alleviate pain"). They expand the previously established mono-lingual methods by introducing cross-lingual methods that use bilingual dictionaries and cross-lingual word embeddings.


2nd Phase of SFB 1102 approved

The collaborative research centre 1102 "Information Density and Linguistic Encoding", funded by the German Research Foundation (DFG), has been granted approx. 11 million euros for a four-year extension starting in July 2018. The CRC directed by Elke Teich brings together around 60 scientists from the fields of Linguistics, Psychology and Computer Science to investigate the hypothesis that language variation and language use can be better understood in terms of a speaker's desire to rationally distribute information across the linguistic signal.


Ausschreibung Fulbright Stipendien

Wer im Studienjahr 2019-2020 für vier bis neun Monate als graduate student an einer US-Hochschule studieren möchte, kann sich jetzt um ein Studienstipendium der Fulbright-Kommission bewerben.
Stipendiat/innen werden mit bis zu $34.500 und der Aufnahme in das Fulbright-Netzwerk unterstützt. Bewerbungsfrist ist der 23. Juli 2018.

The next speaker in the Phonetics Colloquium is Ralph Rose (Waseda University) with a talk on: "Towards providing real-time feedback on speech fluency for L2 learner development" abstract_rose.pdf on Monday, March 12th, 16:00-17:30 (building C7.2, room 5.09).

Alle Bachelorstudenten und -studentinnen der Fachrichtung sind eingeladen, an einer Online-Befragung teilzunehmen, die dazu beitragen wird, die Qualität von Studium und Lehre zu verbessern.

Im Foyer von Gebäude C7 3 ist ab 19. Oktober die Ausstellung "Schriftsysteme" zu sehen. Die Ausstellung gibt einen Überblick über die Verschriftungssysteme verschiedener Sprachen: Alphabete, Gebärden und Melodie, Geheimschriften und Kunstsprachen. Auch die technischen Aspekte von schriftlicher Sprachkodierung werden behandelt.

Die Saarbrücker Computerlinguistik, mittlerweile Teil der Fachrichtung Sprachwissenschaft und Sprachtechnologie, feiert am 28. Oktober in der Aula ihr 25-jähriges Bestehen.

The German Research Foundation (DFG) has granted a three year extension of their funding for Alexander Koller's research project "Efficient statistical parsing and translation for expressive grammatical formalisms with tree automata".


Shared task at SemEval 2018: Machine Comprehension using Commonsense Knowledge

Manfred Pinkal's group is organizing a shared task at next year's SemEval. Reading texts will be provided together with multiple choice questions. Participating systems have to pick the correct answer to each question, given the reading text. This task will require a model to make use of commonsense knowledge.