385 citations · 1.2k across the 34 of their papers we have counts for
41 papers
Open-Domain Dialog Evaluation using Follow-Ups Likelihood
Maxime De Bruyn, Ehsan Lotfi, Jeska Buhmann +1
Automatic evaluation of open-domain dialogs remains an unsolved problem. Moreover, existing methods do not correlate strongly with human annotations. This paper presents a new auto…
CoNTACT: A Dutch COVID-19 Adapted BERT for Vaccine Hesitancy and Argumentation Detection
Jens Lemmens, Jens Van Nooten, Tim Kreutz +1
We present CoNTACT: a Dutch language model adapted to the domain of COVID-19 tweets. The model was developed by continuing the pre-training phase of RobBERT (Delobelle, 2020) by us…
Cyberbullying Classifiers are Sensitive to Model-Agnostic Perturbations
Chris Emmery, Ákos Kádár, Grzegorz Chrupała +1
A limited amount of studies investigates the role of model-agnostic adversarial behavior in toxic content classification. As toxicity classifiers predominantly rely on lexical cues…
Teach Me What to Say and I Will Learn What to Pick: Unsupervised Knowledge Selection Through Response Generation with Pretrained Generative Models
Ehsan Lotfi, Maxime De Bruyn, Jeska Buhmann +1
Knowledge Grounded Conversation Models (KGCM) are usually based on a selection/retrieval module and a generation module, trained separately or simultaneously, with or without havin…
MFAQ: a Multilingual FAQ Dataset
Maxime De Bruyn, Ehsan Lotfi, Jeska Buhmann +1
In this paper, we present the first multilingual FAQ dataset publicly available. We collected around 6M FAQ pairs from the web, in 21 different languages. Although this is signific…
ConveRT for FAQ Answering
Maxime De Bruyn, Ehsan Lotfi, Jeska Buhmann +1
Knowledgeable FAQ chatbots are a valuable resource to any organization. While powerful and efficient retrieval-based models exist for English, it is rarely the case for other langu…