1 code implementation • 2 Aug 2021 • Maxime De Bruyn, Ehsan Lotfi, Jeska Buhmann, Walter Daelemans
While powerful and efficient retrieval-based models exist for English, it is rarely the case for other languages for which the same amount of training data is not available.
1 code implementation • EMNLP (MRQA) 2021 • Maxime De Bruyn, Ehsan Lotfi, Jeska Buhmann, Walter Daelemans
In this paper, we present the first multilingual FAQ dataset publicly available.
no code implementations • EMNLP (NLP4ConvAI) 2021 • Ehsan Lotfi, Maxime De Bruyn, Jeska Buhmann, Walter Daelemans
In this work we study the unsupervised selection abilities of pre-trained generative models (e. g. BART) and show that by adding a score-and-aggregate module between encoder and decoder, they are capable of learning to pick the proper knowledge through minimising the language modelling loss (i. e. without having access to knowledge labels).
1 code implementation • COLING 2022 • Maxime De Bruyn, Ehsan Lotfi, Jeska Buhmann, Walter Daelemans
Automatic evaluation of open-domain dialogs remains an unsolved problem.
no code implementations • 14 Jan 2024 • Ehsan Lotfi, Maxime De Bruyn, Jeska Buhmann, Walter Daelemans
The new wave of Large Language Models (LLM) has offered an efficient tool to curate sizeable conversational datasets.
no code implementations • COLING 2022 • Jeska Buhmann, Maxime De Bruyn, Ehsan Lotfi, Walter Daelemans
In addition, we show that large groups of semantically similar questions are important for obtaining well-performing intent classification models.