Navigationsweiche Anfang

Navigationsweiche Ende

Select language


Natural Language Processing

We seek to push the boundaries in several areas of Natural Language Processing (NLP) by performing both basic research and solving applied problems, partially in cooperation with industry partners.

Natural Language Processing is a cross-disciplinary research field that draws heavily from artificial intelligence (AI), machine learning (ML), mathematics, and linguistics. AI drives the current, fast-paced evolution of language technology. Better capabilities to process natural language are much needed, as humanity’s data production has never been higher. Most of this data is in the form of text (e.g., tweets, blog posts, search queries, and code). Personal assistants, recommender systems, fake news identification, financial stock analysis, chatbots, autocorrection, auto-completion, intelligent search engines, and automatic translation or captioning are just a few examples of how NLP and AI are helping us to manage the flood of data. However, systems to process natural language are far from perfect, which leaves much space for research.

Enabling machines to understand and generate natural language is a challenging task. Natural language is full of nuances and implicit elements that sometimes are hard to grasp, even for humans. However, this makes the problems computers need to solve even more exciting. We believe NLP and AI play a fundamental role in helping humans achieve great things. Therefore, we focus our research on foundational aspects in NLP and solving complex use-case-specific challenges.

Some areas we are working in are:

Basic ResearchApplications
  • Language Modeling
  • Natural Language Understanding
  • Semantic Feature Extraction
  • Text Classification
  • Text Summarization/Generation
  • Word Sense Disambiguation
  • Sentiment Analysis
  • CoReference Resolution
  • Meta-analysis of NLP research
  • Paraphrase and Plagiarism Detection
  • Media Bias Analysis
  • Fake News Detection
  • Trend/News Pattern Identification
  • Identification of toxic individuals
  • Low-resource Language Applications
  • Literature Review Automation
  • Explainable NLP/AI
  • Ethics, bias, and broader impact of NLP
zuletzt bearbeitet am: 02.05.2022