News | Jobs | Team | Grants

Natural Language Understanding

The Natural Language Understanding group works at the intersection of machine learning and natural language processing, with an emphasis on representation learning for the meaning of language, attention-based deep learning models, and structured prediction.

In our group, we model summarization, abstraction (textual entailment), machine translation, knowledge extraction, syntactic structure, and lexical semantics, among other natural language processing (NLP) problems. We develop deep learning models of the discovery and prediction of entities and their relations at multiple levels of representation for multiple tasks.

Group News

How do Large Language Models Represent Information?

research — last modified Nov 11, 2024

Pretrained LLMs have demonstrated impressive abilities, but it is hard to understand how they work or how well they will generalise to a new domain. Idiap researchers are developing a model of how information is represented inside LLMs. By identifying and removing unreliable information, this model can improve generalisation to new domains, without the need or any additional training.

Why do Transformers work so well?

research — last modified Mar 08, 2024

Bayesian Language Understanding with Nonparametric Variational Transformers - Talk Jan 29 2024

Towards energy-efficient artificial intelligence models

research — Jul 26, 2023

As artificial intelligence technologies reach everyday new performances, their energy cost is also increasing significantly. Idiap researchers are proposing a novel approach to address this challenge during a period of rising energy costs.

Idiap is looking for its next director

institute — Jan 14, 2022

Idiap Research Institute and the School of Engineering at EPFL invite applications for the directorship of Idiap. The successful candidate will also hold a faculty position as full professor at EPFL School of Engineering.

A novel architecture to improve syntactic analysis

research — last modified Apr 21, 2021

Demonstrating a significant improvements over the previous state-of-the-art results, James Henderson and Alireza Mohammadshahi of the Natural language understanding group propose a novel approach. Their work was presented during the 16th Conference of the European Chapter of the Association for Computational Linguistics (EACL) on April 21, 2021.

More News

Group Job Openings

Our group is regularly posting job openings ranging from internships to researcher positions. To check the opportunities currently available or to submit a speculative applications use the link below.Our group is regularly posting job openings ranging from internships to researcher positions. To check the opportunities currently available or to submit a speculative applications use the link below.