EACL 2014 Workshop on
Cognitive Aspects of Computational Language Learning
April 26, 2014
The past decades have seen a massive expansion in the application of statistical and machine learning methods to natural language processing (NLP). This work has yielded impressive results in numerous speech and language processing tasks, including e.g. speech recognition, morphological analysis, parsing, lexical acquisition, semantic interpretation, and dialogue management. The good results have generally been viewed as engineering achievements.
Recently researchers have begun to investigate the relevance of computational learning methods for research on human language acquisition and change. The use of computational modeling is a relatively recent trend boosted by advances in machine learning techniques, and the availability of resources like corpora of child and child-directed sentences, and data from psycholinguistic tasks by normal and pathological groups. Many of the existing computational models attempt to study language tasks under cognitively plausible criteria (such as memory and processing limitations that humans face), and to explain the developmental stages observed in the acquisition and evolution of the language abilities. In doing so, computational modeling provides insight into the plausible mechanisms involved in human language processes, and inspires the development of better language models and techniques.
These investigations are very important since if computational techniques can be used to improve our understanding of human language acquisition and change, these will not only benefit cognitive sciences in general but will reflect back to NLP and place us in a better position to develop useful language models.
Success in this type of research requires close collaboration between the NLP, linguistics, psychology and cognitive science communities.
First Call for Papers
Deadline for Paper Submissions: January 23, 2014 (11:59pm GMT -12)
The workshop is targeted at anyone interested in the relevance of computational techniques for understanding first, second and bilingual language acquisition and language change in normal and clinical conditions. Long and short papers are invited on, but not limited to, the following topics:
— Computational learning theory and analysis of language learning and organization
— Computational models of first, second and bilingual language acquisition
— Computational models of language changes in clinical conditions
— Computational models and analysis of factors that influence language acquisition and use in different age groups and cultures
— Computational models of various aspects of language and their interaction effect in acquisition, processing and change
— Computational models of the evolution of language
— Data resources and tools for investigating computational models of human language processes
— Empirical and theoretical comparisons of the learning environment and its impact on language processes
— Cognitively oriented Bayesian models of language processes
— Computational methods for acquiring various linguistic information (related to e.g. speech, morphology, lexicon, syntax, semantics, and discourse) and their relevance to research on human language acquisition
— Investigations and comparisons of supervised, unsupervised and weakly-supervised methods for learning (e.g. machine learning, statistical, symbolic, biologically-inspired, active learning, various hybrid models) from a cognitive perspective
We invite three different submission modalities:
— Regular long papers
— Regular short papers
— System demonstration
All submissions must be in PDF format and must follow the EACL 2014 formatting requirements (available at http://www.eacl2014.org/files/eacl-2014-styles.zip).
Reviewing will be double-blind, and thus no author information should be included in the papers; self-reference should be avoided as well. Papers that do not conform to these requirements will be rejected without review. Accepted papers will appear in the workshop proceedings, where no distinction will be made between papers presented orally or as posters.
Submissions must be uploaded onto the START system by the submission deadline:
January 23, 2014 (11:59pm GMT -12 hours)
Jan 23, 2014: Long and short paper submission deadline
Feb 05, 2014: System demonstrations submission deadline
Feb 20, 2014: Notification of acceptance
Mar 03, 2014: Camera-ready deadline
Apr 26, 2014: Workshop
Workshop Organizers and Contact:
Alessandro Lenci (University of Pisa, Italy)
Muntsa Padró (Federal University of Rio Grande do Sul, Brazil)
Thierry Poibeau (LATTICE-CNRS, France)
Aline Villavicencio (Federal University of Rio Grande do Sul, Brazil)
For any inquiries regarding the workshop please send an email to cognitive2014gmail.com.