This workshop focuses on the common space delimited by two areas, natural language processing and deep learning, and considers linguistic complexity and its relevance in the field of NLP. The main goal of the workshop is to promote interdisciplinarity among people working in such disciplines, boosting the interchange of knowledge and viewpoints between specialists. We propose a cross-discipline workshop that foster exchange of ideas between people in the area of deep learning and natural language processing and people dealing with natural language complexity from a cognitive or a theoretical point of view.
For a long time, NLP techniques were dominated by linear modeling approaches to supervised learning (e.g., linear SVM or logistic regression). However, NLP is being revolutionized by deep learning approaches, with which have been achieved superior results across many different NLP tasks as compared to traditional machine learning approaches.
Complexity has become an important concept in several scientific disciplines. There has been a lot of research on complexity and complex systems in the natural and social sciences and now also in linguistics. Linguistic complexity may be a key point in automatic natural language processing, since results in that field may condition the design of language technologies. However, currently, there is no clear solution to quantify the complexity of natural languages.
In this workshop, we are interested in contributions introducing new formal and/or computational models and measures to assess natural languages complexity (in human and automatic language processing) and results in applying deep learning methods for solving NLP tasks. We will also encourage works that present new developments in applying NLP for solving problems related to Deep Learning.