Proceedings of KONVENS 2012
The proceedings are now available online.
REGISTRATION IS OPEN
Please register as soon as possible to get the early registration bonus.
The Conference on Natural Language Processing ("Konferenz zur Verarbeitung Natürlicher Sprache", KONVENS) aims at offering a broad perspective on current research and developments within the interdisciplinary field of natural language processing. It allows researchers from all disciplines relevant to this field of research to present their work.
The KONVENS is held in a two year rotation, organized by the scientific societies DGfS-CL (German Society for Linguistics, Section Computational Linguistics), GSCL (Society for Language Technology and Computational Linguistics) and ÖGAI (Austrian Society for Artificial Intelligence).
We welcome contributions on research, development, applications and evaluation, covering all areas of natural language processing, ranging from basic questions to practical implementations of natural language resources, components and systems.
Central theme of the 11th KONVENS is
Empirical methods in natural language processing.
We especially encourage the submission of contributions proposing new methods for learning from substantial amounts of natural language (including speech) data, be they annotated or un-annotated, as well contributions relating to evaluation of such methods.
The conference language is English. We welcome and encourage international submissions.
We are happy to announce that the following researchers have accepted our invitation as invited speakers:
RWTH Aachen University, Aachen
DIGITEO Chair, LIMSI-CNRS, Paris
The Statistical Approach to Natural Language Processing:
Achievements and Open Problems
When IBM research presented a statistical approach to French-English machine translation in 1988, the linguistic community was shocked because this approach was a hit in the face of the then received machine translation theories. Since then we have seen a dramatic progress in statistical methods for speech recognition, machine translation and other tasks in natural language processing. This talk gives an overview of the underlying statistical methods. In particular, the talk will focus on the remarkable fact that, for all these tasks, the statistical approach makes use of the same four principles:
- Bayes decision rule for minimum error rate,
- probabilistic models, e.g. Hidden Markov models or conditional random fields, for handling strings of observations (like acoustic vectors for speech recognition and written words for language translation),
- training criteria and algorithms for estimating the free model parameters from large amounts of data,
- the generation or search process that generates the recognition or translation result.
Università di Trento
Compositionality in (high-dimensional) space
Formal semanticists have developed sophisticated compositional theories of sentential meaning, paying a lot of attention to those grammatical words (determiners, logical connectives, etc.) that constitute the functional scaffolding of sentences. Corpus-based computational linguists, on the other hand, have developed powerful distributional methods to induce representations of the meaning of content-rich words (nouns, verbs, etc.), typically discarding the functional scaffolding as "stop words". Since we do not communicate by logical formulas, nor, Tarzan-style, by flat concatenation of content words, a satisfactory model of the semantics of natural language should strike a balance between the two approaches. In this talk, I will present some recent proposals that try to get the best of both worlds by adapting the classic view of compositionality as function application developed by formal semanticists to distributional models of meaning. I will present preliminary evidence of the effectiveness of these methods in scaling up to the phrasal and sentential domains, and discuss to what extent the representations of phrases and sentences we get out of compositional distributional semantics are related to what formal semanticists are trying to capture.
Related and Co-Located Events
FAA 2012 ("The ACM 3rd International Symposium on Facial Analysis and Animation") in Vienna, Austria, September 21.
DAGM/OAGM 2012 ("Third Joint Pattern Recognition Symposium") in Graz, Austria, from August 28-31.
TSD 2012 ("Text, Speech and Dialogue") in Brno, Czech Republic, from September 3-7.
GMW 2012 ("Jahrestagung der Gesellschaft für Medien in der Wissenschaft") in Vienna, Austria from September 10-13.
KI 2012 ("35th German Conference on Artificial Intelligence") in Saarbrücken, Germany from September 24-27.