Human communication is multimodal and occurs through speech, language, gesture, facial expression, and similar signals. To enable natural interactions with human beings, artificial agents must be capable of analysing and producing these rich and interdependent signals and connecting them to their semantic implications. STING aims to unify synthesis and analysis through transducers and invertible neural models, connecting concrete, continuous-valued sensory data such as images, sound, and motion, with high-level, predominantly discrete representations of meaning. The project has the potential to endow synthesis output with human-understandable high-level explanations while simultaneously improving the ability to attach probabilities to semantic representations.
Funded by WASP
Today, neural networks are the most important computational paradigm for AI and machine learning. While their computational power has been studied for decades, the theoretical development has not been able to keep up with the recent upshot of new neural architectures, such as the Transformer. Also, existing theoretical results are of limited practical value because they often apply to monolithic architectures, whereas applications typically use networks composed of re-usable components. Moreover, theoretical results tend to make idealising assumptions such as infinite precision or unlimited training time rather than acknowledging that such commodities are in short supply and should thus be treated as parameters of expressive power. In this project, we want to address these shortcomings and develop a practical theory of computation for modern neural network architectures. The project combines methods from theoretical computer science – especially the theory of computation and formal languages – with empirical validation in natural language processing (NLP).
Funded by WASP
Building computers that understand human language is one of the central goals of artificial intelligence. A recent breakthrough on the way towards this goal is the development of neural models that learn deep contextualized representations of language. However, while these models have substantially advanced the state of the art in natural language processing (NLP), our understanding of the learned representations and our repertoire of techniques for integrating them with other knowledge representations and reasoning facilities remain severely limited. To address these gaps, we will develop new methods for interpreting, grounding, and integrating deep contextualized representations of language and evaluate the usefulness of these methods in the context of threat intelligence applications together with our industrial partner.
Funded by WASP
See all publications
Our teaching portfolio comprises courses and degree projects in natural language processing and text mining at the basic, advanced, and doctoral levels. We are committed to excellence in teaching through effective pedagogy that fosters relevant knowledge and skills and stimulate students to drive their own learning process.
Writing computer programs that understand and produce human language is a central goal of artificial intelligence. This course aims to provide an understanding of how far we are from this goal: what is and what is not possible today. Students will learn about current methods in natural language processing, about what resources are required to build language technology systems, and about how one can assess the quality of these methods and systems.
Course website ETE335
Language technology – technology for the analysis and interpretation of natural language – forms a key component of smart search engines, personal digital assistants, and many other innovative applications. The goal of this course is to give an introduction to language technology as an application area, as well as to its basic methods. The course focuses on methods that process text.
Natural Language Processing (NLP) develops methods for making human language accessible to computers. This course aims to provide students with a theoretical understanding of and practical experience with the advanced algorithms that power modern NLP. The course focuses on methods based on deep neural networks.
Course website TDDE09
Text Mining is about distilling actionable insights from text. The overall aim of this course is to provide students with practical experience of the main steps of text mining: information retrieval, processing of text data, modelling, analysis of experimental results. The course ends with an individual project where students work on a self-defined problem.
Natural Language Processing (NLP) develops methods for making human language accessible to computers. The goal of this course is to provide students with a theoretical understanding of and practical experience with the advanced algorithms that power modern NLP. The course focuses on methods based on deep neural networks.
This course is given in the context of the WASP Graduate School.
Current large language models can tackle a broad range of tasks. However, they are known to hallucinate and sometimes have difficulties reasoning over knowledge. Models that retrieve and integrate information from knowledge graphs have been viewed as one alternative to ground language models on external knowledge, making language models more consistent and potentially leveraging the graph structure for reasoning.
Our group has developed a new set of tools for analyzing multimodal language and knowledge graph models and found that current state-of-the-art models do not utilize both modalities efficiently. This could be due to current training datasets and model designs. This project aims to address this gap. The project will use our newly developed tools to develop new model architectures, training regimes, and datasets that make the models use both modalities.
Successfully grounding language models in external knowledge bases is an important research problem. Therefore, the work done in this project is of great value to our group and the broader research community.
Contact: Oskar Holmström
Parameter-efficient fine-tuning techniques such as adapters are increasingly popular as LLMs become larger and more powerful. They not only make the fine-tuning more cost-efficient and climate-friendly but also help preserve the models’ general capabilities and avoid catastrophic forgetting. In this project, you implement and compare different approaches to adapting a model to specific languages and evaluate them on multilingual datasets for different tasks and domains. You will join an ongoing project in our group and help us to improve our results and/or get new insights on where language adapters are useful.
Contact: Jenny Kunz
Identifying which language a text is written in sounds like a solved problem: most translation tools, for example, can automatically detect the language of the source text. However, language identification methods only tend to work reliably on longer inputs, such as documents or full sentences. There are many situations in which we might want to identify languages on a more fine-grained level, for example:
In this project, you will apply modern algorithms and machine learning techniques to try to improve language identification on a word or phrase level in mixed-language data. There are several ways you can approach this project:
Contact: Marcel Bollmann