The Computational Linguistics & Psycholinguistics Research Group of the University of Antwerp (CLiPS, http://www.clips.uantwerpen.be) focuses on applications of statistical and machine learning methods, trained on corpus data, to explain human language acquisition and processing data, and to develop automatic text analysis systems that are accurate, efficient, and robust enough to be used in practical applications.
There are 3 subgroups to CLiPS: (1) the sociolinguistics group studies language variation in different demographic groups. The (2) psycholinguistics group studies the effect of cochlear implantation on child language acquisition. This description focuses on (3) the computational linguistics group.
Current research at CLiPS' Computational Linguistics Group focuses on developing tools that can extract data from social media messages, such as fine-grained sentiment analysis, and the detection of subversive behavior on social network sites (sexually transgressive behavior, hate speech, ...). Furthermore, CLiPS is well known for its work on computational stylometry and has developed state-of-the-art technology for authorship attribution, as well as author profiling, i.e. the detection of personality, age and gender of the author of a text, based on personal writing style. Another line of research at CLiPS focuses on computational psycholinguistics and researches psychologically plausible models of child language acquisition and bilinguality. CLiPS also researches and develops tools for biomedical text mining.
Over the years, CLiPS has established a strong reputation in the application of machine learning methods on a variety of language technology problems for a wide range of languages. To capitalize on this reputation, a spin-off company, Textgain (textgain.com), was founded in 2015 that aims to bring CLiPS technology to the market for commercial purposes.
- Twitter: Don't write a tweet, but don't write a book either. Try to write an engaging two pager, with flowing paragraphs of concise sentences that don't use 'would', 'could' or 'should'.
Tell us a little bit about yourself. What are you studying and why? Where do you want to be in 10 years from now? Do you believe robots will ever have feelings? How many years have you been writing code? (we like Python, and possibly C to speed things up). Do you have other relevant skills (languages, psychology, statistics, visualization, web development, project management, lawmaking ...)? You can also add your cv, but these are tedious to examine and difficult to compare. We prefer that you first of all write something engaging about yourself!
Tell us how you will tackle the challenge. Be bold, tell us about your own ideas on how we should be dealing with the challenge. Talk about things that you want to do, not what you think we want to hear. Propose a rough timeline with some goals and intermediate milestones. Don't add a lengthy day-to-schedule – plans tend to change. Mention any papers you have read or published on the topic. Tell us what ML algorithms, NLP techniques and open source toolkits you know of.
If you fear that you don't have the required skills and knowledge, but you really, really want to be involved, tell us why, and think of ways you can contribute while learning the ropes. Motivation is very contagious.