Welcome to the AI4LT

The "Artificial Intelligence for Language Technologies (AI4LT)" lab at the Institute for Anthropomatics und Robotics (IAR) develops language technologies that enable human-computer interaction and support human-human interaction using deep learning. The lab investigates the research areas: machine translation, speech translation, automatic speech recognition and dialog modelling. The lab is headed by Prof. Dr. Jan Niehues.


Information about research areas, projects and publications


Information about lectures and bachelor/master theses topics


Get to know our team




Paper in Machine Translation Summit: Perturbation-Based Quality Estimation

Quality estimation is the task of predicting the quality of machine translation outputs without relying on any gold translation references. We propose an explainable, unsupervised word-level quality estimation method for blackbox machine translation. It can evaluate any type of blackbox MT systems, including the currently prominent large language models (LLMs) with opaque internal processes. See the paper (link) for details!

Looking for a new colleague!

We are looking for a PhD candidate (Akademische/r Mitarbeiter/in; all genders) in the field of natural language processing (large language models, multimodal language processing). Check out this link for details!

WMT Publication: Can we learn an artificial language?

The cornerstone of multilingual neural translation is shared representations across languages. In this work, we discretize the encoder output latent space of multilingual models by assigning encoder states to entries in a codebook, which in effect represents source sentences in a new artificial language (Link). Join the presentation on Wednesday, 07.12.2022 at 14:20 GST (11:20 CET) at the Seventh Conference on Machine Translation (WMT 2022).

Pre-trained Speech Translation
NeurIPS workshop paper: Efficient Speech Translation with Pre-trained Models

Pre-trained models are a promising approach to efficiently build speech translation models for many different tasks. Zhaolin Li showed how this models can be used using limited data and computation resources (Link). Join his presentation on Friday, 02.12.2022 between 7:30pm - 8:30pm CET at the Workshop Second Workshop on Efficient Natural Language and Speech Processing (ENLSP-II).


The "AI for Language Technologies" was found on 01.03.2022. We are looking foward to exciting reseearch and teaching at KIT.