CLiPS, University of Antwerp
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.
CLiPS, University of Antwerp 2019 Projects
Adversarial Examples for Natural Language ModelsMeaningful Adversarial Examples for Natural Language Models A project to create adversarial examples and resulting counterfactuals for text...
Cross-language analysis of U.S.-Russian relations via Twitter (Task 3) or early Alzheimer syndrome detection in speech analysis (Task 9)Cross-language analysis of U.S.-Russian relations (Task 3) Tweets from US democrats (or just anyone actively opposing Trump's presidency) and Russian...
Hate Speech Annotation and Automatic Assessment: Resource and Best Practices DevelopmentIn the wake of the research I have undertaken for my Master's degree's thesis on automatic detection and assessment of right-wing extremists' online...
viNLaP: An interactive visualizer for polarized data sourcesviNLaP is an interactive and data-driven web dashboard with three modules, each one based on one of these three main analysis: Spatial, Temporal and...