Language AI
“Language AI is transforming how humans interact with technology. We explore how machines can understand, process, and generate language – and turn these advances into robust solutions for real-world applications.”
Expertise and Services
Expertise
- Dialogue systems
- Speech processing
- Social media analysis
- Evaluation of Large Language Models (LLMs)
The Language AI research team develops technologies for the analysis, understanding and generation of speech and text. We combine methods from linguistics, natural language processing (NLP) and artificial intelligence to enable natural language communication between humans and machines. In our research, we work on topics such as text classification (e.g. sentiment analysis), chatbots/dialogue systems, text summarization, speech-to-text, speaker diarization and natural language generation. The group particularly focuses on Swiss German speech and text processing.
Services
- Research and development: small to large-scale collaborative projects, third party-funded research, student projects, commercially applicable prototypes
- Insight: keynotes, trainings
- AI consultancy: workshops, expert support, advice, technology assessment
Team
Head of Research Group
Projects
-
Swiss German Speech Processing for Persons with Speech Disorders (SpeeDi)
We will develop language technologies for imperfect Swiss German speech. These technologies are crucial to build AI applications for persons with speech disorders, e.g chatbots for children in speech therapy or diagnosis tools for patients with Parkinson’s Disease.
current, 06/2026 - 05/2029
-
Multikom XR – Exploratory study on AI-supported analysis of professional communication in XR
The project investigates the feasibility of AI-supported conversation simulations in XR for professional communication training. The innovative focus is on capturing and evaluating para- and nonverbal communication signals.
current, 09/2025 - 02/2027
-
A novel procedure to support meaning-making at work: combining work and life design research with AI-enhanced narrative methods
We are developing a digital platform called “Meaning@Work”, which supports employees in shaping their work and careers in a meaningful way.
current, 04/2025 - 02/2028
-
Jill & Jules: Engaging young voters
Jill & Jules are a two relatable AI characters who motivate young Swiss voters. By presenting referendums through interactive, informal conversations in Swiss German, Jill & Jules make complex or seemingly mundane topics accessible and engaging.
expired, 03/2025 - 02/2026
-
NLP Community Building (ComBi)
SwissNLP would like to take concerted action to better network Swiss players from industry, science and administration in the field of Natural Language Processing (NLP). For this reason various activities are to be carried out until the end of 2025 such as expert group meetings, applied conferences,…
current, 12/2023 - 01/2027
-
AI for self-organizing Content Platform (AI4CP)
expired, 05/2023 - 11/2023
-
Towards a Voice-Based Chatbot for Language Learners (ChaLL)
We take first steps towards developing ChaLL, a voice-based chatbot that provides language learners with opportunities to practice speaking in both focused and unfocused task-based conversations and receive feedback, free from the time constraints and pressures of the traditional classroom setting.
expired, 02/2023 - 07/2024
-
PRISM: Predicting Radicalization Events in Social Media User Timelines
The PRISM project focuses on detecting radicalization events in Social Media networks. Overall, we are interested in unveiling the mechanics that lead to the event of extremist ideology being transferred and incorporated into a social media user’s world view. Specifically, the proposed project aims…
expired, 04/2022 - 02/2023
-
DOSSMA – Detection of Suspicious Social Media Activities
The DOSSMA project will investigate suspicious and malicious behaviour on social media platforms. In a first phase, we will compile an extensive survey report on the areas that are currently being researched, including the respective state-of-the-art, existing solutions and initiatives. This report…
expired, 05/2021 - 12/2021
-
Speech-to-Text for Swiss German
expired, 02/2021 - 02/2022
-
Virtual Kids - Virtual characters to improve the quality of child interrogations
If children are questioned in preliminary proceedings about their own experiences or observations relevant to criminal law, it depends decisively on the quality of the questioning whether their statements can be used in criminal proceedings or whether decisions can be made on this basis and…
expired, 04/2020 - 04/2024
-
AuSuM – Automatic Supply Chain Monitoring
The project implements an online service for companies to monitor suppliers for violations ofenvironmental, social, or governance norms. To do so, a vast variety of sources, such as news outlets, is monitored using machine learning and natural language processing with near human-level accuracy.
expired, 12/2018 - 05/2021
-
Pre-Study on Generation of Hockey News
Tamedia would like to develop a software system that automatically generates news articles from hockey game data.ZHAW will explore the different state-of-the-art technologies to evaluate the feasibility of developing a natural language system that generates rich contextual ice hockey game report…
expired, 10/2018 - 12/2019
-
Digital communication strategies for the cultural sector in the Lake Constance region
This research project will investigate how a communication strategy for the marketing and communication of the diverse cultural activities and sites in the Lake Constance region could be shaped.For a sustainable strategy development the digitization of the communication, by which also the cultural…
expired, 07/2018 - 06/2020
-
Call-E – Virtual Call Agent
The industrial project partner offers online brokering of loans, mortgages and insurances. The brokering process involves several phone calls of a call agent with a potential client. This is time-consuming and highly repetitive. For this reason, we want to develop a dialogue system which can take…
expired, 06/2018 - 05/2020
-
Natural Language Processing for Tumor Classification (NLP4TC)
Entry, discharge, radiology and pathology reports and other clinical documents are a valuable resource to be harvested for precision medicine. They are typically stored in a free text format, only little structure is imposed and terminology is heterogeneous. We will apply natural language…
expired, 05/2018 - 12/2019
-
SCAI – Smart Contract Analytics using Artificial Intelligence
In the SCAI project, ZHAW and legartis investigate how content of contracts can automatically be evaluated legally by applying methods from the areas of Natural Language Processing and Deep Learning.
expired, 05/2018 - 05/2020
-
LIHLITH – Learning to Interact with Humans by Lifelong Interaction with Humans
The LIHLITH project is a fundamental pilot research project which introduces a new lifelong learning framework for the interaction of humans and machines on specific domains. A Lifelong Learning system learns different tasks sequentially, over time, getting better at solving future related tasks…
expired, 10/2017 - 12/2020
-
Libra: A One-Tool Solution for MLD4 Compliance
Compared with earlier regulations, the 4th European Money Laundering Directive (MLD4) imposes rigorously increased requirements. It compels obliged entities to conduct in depth screenings of customers and their associations. The Libra Project aims at providing a one tool solution for meeting MLD4…
expired, 09/2016 - 05/2019
-
DeepText: Intelligent Text Analysis with Deep Learning
DeepText develops a software framework to automatically analyse texts in order to extract important information. The framework comprises modern algorithms from the field of machine learning (deep learning) that are better at analyzing texts than traditional approaches. They can for example be used…
expired, 09/2016 - 02/2018
Publications
-
Hürlimann, Manuela; Cieliebak, Mark,
2026.
In:
Mille, Simon; Gehrmann, Sebastian; Schmidtová, Patrícia; Dušek, Ondřej; Fadaee, Marzieh; Lo, Kyle; Santus, Enrico; Stanovsky, Gabriel, eds.,
Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics (GEM).
Fifth Workshop on Generation, Evaluation and Metrics (GEM), San Diego, USA, 2-3 July 2026.
Association for Computational Linguistics.
pp. 1111-1116.
Available from: https://doi.org/10.21256/zhaw-36904
-
Schmid, Lars; von Däniken, Pius; Giedemann, Patrick; Tuggener, Don; Bühler, Judith; Kamenowski, Maria; Girschik, Katja; Baier, Dirk; Cieliebak, Mark,
2025.
HICC : a dataset for German hate speech in conversational context[paper].
In:
Proceedings of the 21st Conference on Natural Language Processing (KONVENS 2025).
21st Conference on Natural Language Processing (KONVENS), Hannover, Germany, 9-12 September 2025.
Association for Computational Linguistics.
pp. 168-176.
Available from: https://doi.org/10.21256/zhaw-35860
-
Stucki, Samuel; Deriu, Jan; Cieliebak, Mark,
2025.
Voice adaptation for Swiss German[paper].
In:
Proceedings Interspeech 2025.
Interspeech 2025, Rotterdam, The Netherlands, 17-21 August 2025.
International Speech Communication Association.
pp. 4143-4147.
Available from: https://doi.org/10.21256/zhaw-36147
-
von Däniken, Pius; Deriu, Jan Milan; Cieliebak, Mark,
2025.
A measure of the system dependence of automated metrics[paper].
In:
Che, Wanxiang; Nabende, Joyce; Shutova, Ekaterina; Pilehvar, Mohammad Taher, eds.,
Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers).
63rd Annual Meeting of the Association for Computational Linguistics (ACL), Vienna, Austria, 27 July - 1 August 2025.
Association for Computational Linguistics.
pp. 87-99.
Available from: https://doi.org/10.21256/zhaw-36126
-
Cieliebak, Mark; Gerber, Jonathan; Hürlimann, Manuela,
2025.
SwissCoco2025 : the Swiss Corpora Collection 2025[paper].
In:
Gerber, Jonathan; Cieliebak, Mark; Tuggener, Don; Hürlimann, Manuela, eds.,
Proceedings of the 10th edition of the Swiss Text Analytics Conference.
10th Swiss Text Analytics Conference – SwissText 2025, Winterthur, Switzerland, 13-15 May 2025.
Association for Computational Linguistics.
pp. 133-148.
Available from: https://doi.org/10.21256/zhaw-36110