1 citations · 1 across the 3 of their papers we have counts for
3 papers
Catastrophic-risk-aware reinforcement learning with extreme-value-theory-based policy gradients
Parisa Davar, Frédéric Godin, Jose Garrido
This paper tackles the problem of mitigating catastrophic risk (which is risk with very low frequency but very high severity) in the context of a sequential decision making process…
Zero-Shot Cross-Lingual Sentiment Classification under Distribution Shift: an Exploratory Study
Maarten De Raedt, Semere Kiros Bitew, Fréderic Godin +2
The brittleness of finetuned language model performance on out-of-distribution (OOD) test samples in unseen domains has been well-studied for English, yet is unexplored for multi-l…
IDAS: Intent Discovery with Abstractive Summarization
Maarten De Raedt, Fréderic Godin, Thomas Demeester +1
Intent discovery is the task of inferring latent intents from a set of unlabeled utterances, and is a useful step towards the efficient creation of new conversational agents. We sh…