Text mining and data harvesting algorithms have become popular in the computational linguistics community. They employ patterns that specify the kind of information to be harvested, and usually bootstrap either the pattern learning or the term harvesting process (or both) in a recursive cycle, using data learned in one step to generate more seeds for the next. They therefore treat the source te...

We present three ways of inducing probability distributions on derivation trees produced by Minimalist Grammars, and give their maximum likelihood estimators. We argue that a parameterization based on locally normalized log-linear models balances competing requirements for modeling expressiveness and computational tractability.

1. Basics: Computational Linguistics (CL) between research and technology 2. Application field 2.1 The paradigm of Machine Translation (MT) and the desire for overcoming the language barriers 2.1.1 The technological situation 2.1.2 Short overview of the history of machine translation 2.1.3 Goals for research in MT 2.2 The paradigm of Natural Language Understanding 2.3 Mainstream Topics of Compu...

Corpus linguistics has been in the spotlight for the last decade, with the usage of modern computers and technologies deeper understanding of languages can be obtained. Corpus linguistics helps language teaching for acquiring a better view for language. Language teachers will know what sequence of words and patters tend to co-occur. Unlike previous enormous lists of words which students were fo...

Many tasks in computational linguistics traditionally rely on hand-crafted or curated resources like thesauri or word-sense-annotated corpora. The availability of big data, from the Web and other sources, has changed this situation. Harnessing these assets requires scalable methods for data and text analytics. This paper gives an overview on our recent work that utilizes big data methods for en...

This paper discusses experiences from supplementing the Computational Linguistics (CL) curriculum at five German universities with distance education in the form of a network of online courses. The courses were developed and taught within the Germany-wide joint project MiLCA (Medienintensive Lehrmodule in der Computerlinguistik-Ausbildung, media-intensive teaching-modules for education in CL, [...

Linguistics olympiads, now offered in more than 20 countries, provide secondary-school students a compelling introduction to an unfamiliar field. The North American Computational Linguistics Olympiad (NACLO) includes computational puzzles in addition to purely linguistic ones. This paper explores the computational subject matter we want to convey via NACLO, as well as some of the challenges tha...