activity
20182022
most citedOn the Origin of Hallucinations in Conversational Models: Is it the Datasets or the Models?

13 citations · 24 across the 2 of their papers we have counts for

collaborators

5 papers

cs.CL202213 cited

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…

cs.LG202111 cited

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…

cs.CL2021

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…

cs.CL2019

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…

cs.CL2018

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…