13 citations · 24 across the 2 of their papers we have counts for
5 papers
On the Origin of Hallucinations in Conversational Models: Is it the Datasets or the Models?
Nouha Dziri, Sivan Milton, Mo Yu +2
Knowledge-grounded conversational models are known to suffer from producing factually invalid statements, a phenomenon commonly called hallucination. In this work, we investigate t…
Decomposed Mutual Information Estimation for Contrastive Representation Learning
Alessandro Sordoni, Nouha Dziri, Hannes Schulz +3
Recent contrastive representation learning methods rely on estimating mutual information (MI) between multiple views of an underlying context. E.g., we can derive multiple views of…
Neural Path Hunter: Reducing Hallucination in Dialogue Systems via Path Grounding
Nouha Dziri, Andrea Madotto, Osmar Zaiane +1
Dialogue systems powered by large pre-trained language models (LM) exhibit an innate ability to deliver fluent and natural-looking responses. Despite their impressive generation pe…
Evaluating Coherence in Dialogue Systems using Entailment
Nouha Dziri, Ehsan Kamalloo, Kory W. Mathewson +1
Evaluating open-domain dialogue systems is difficult due to the diversity of possible correct answers. Automatic metrics such as BLEU correlate weakly with human annotations, resul…
Augmenting Neural Response Generation with Context-Aware Topical Attention
Nouha Dziri, Ehsan Kamalloo, Kory W. Mathewson +1
Sequence-to-Sequence (Seq2Seq) models have witnessed a notable success in generating natural conversational exchanges. Notwithstanding the syntactically well-formed responses gener…