no code implementations • CLASP 2022 • Claudio Greco, Alberto Testoni, Raffaella Bernardi, Stella Frank
Pre-trained Vision and Language Transformers achieve high performance on downstream tasks due to their ability to transfer representational knowledge accumulated during pretraining on substantial amounts of data.
no code implementations • EMNLP (SpLU) 2020 • Alberto Testoni, Claudio Greco, Tobias Bianchi, Mauricio Mazuecos, Agata Marcante, Luciana Benotti, Raffaella Bernardi
By analyzing LXMERT errors and its attention mechanisms, we find that our classification helps to gain a better understanding of the skills required to answer different spatial questions.
1 code implementation • ACL (splurobonlp) 2021 • Tianai Dong, Alberto Testoni, Luciana Benotti, Raffaella Bernardi
We call the question that restricts the context: trigger, and we call the spatial question that requires the trigger question to be answered: zoomer.
1 code implementation • COLING 2022 • Michael Hanna, Federico Pedeni, Alessandro Suglia, Alberto Testoni, Raffaella Bernardi
This paves the way for a systematic way of evaluating embodied AI agents that understand grounded actions.
1 code implementation • 11 Mar 2024 • Alberto Testoni, Juell Sprott, Sandro Pezzelle
While human speakers use a variety of different expressions when describing the same object in an image, giving rise to a distribution of plausible labels driven by pragmatic constraints, the extent to which current Vision \& Language Large Language Models (VLLMs) can mimic this crucial feature of language use is an open question.
no code implementations • 9 Feb 2024 • Alberto Testoni, Raquel Fernández
Clarification questions are an essential dialogue tool to signal misunderstanding, ambiguities, and under-specification in language use.
no code implementations • 24 Oct 2022 • Amit Kumar Chaudhary, Alex J. Lucassen, Ioanna Tsani, Alberto Testoni
Decoding strategies play a crucial role in natural language generation systems.
1 code implementation • EMNLP 2021 • Alberto Testoni, Raffaella Bernardi
Inspired by the cognitive literature on information search and cross-situational word learning, we design Confirm-it, a model based on a beam search re-ranking algorithm that guides an effective goal-oriented strategy by asking questions that confirm the model's conjecture about the referent.
no code implementations • ACL 2021 • Alberto Testoni, Raffaella Bernardi
We also analyse where hallucinations tend to occur more often through the dialogue: hallucinations are less frequent in earlier turns, cause a cascade hallucination effect, and are often preceded by negative answers, which have been shown to be harder to ground.
no code implementations • 20 Mar 2021 • Alberto Testoni, Raffaella Bernardi
Despite important progress, conversational systems often generate dialogues that sound unnatural to humans.
1 code implementation • EACL 2021 • Alberto Testoni, Raffaella Bernardi
When training a model on referential dialogue guessing games, the best model is usually chosen based on its task success.
no code implementations • WS 2020 • Mauricio Mazuecos, Alberto Testoni, Raffaella Bernardi, Luciana Benotti
Regarding our first metric, we find that successful dialogues do not have a higher percentage of effective questions for most models.
no code implementations • WS 2020 • Mauricio Mazuecos, Alberto Testoni, Raffaella Bernardi, Luciana Benotti
Task success is the standard metric used to evaluate these systems.
no code implementations • WS 2019 • Alberto Testoni, S Pezzelle, ro, Raffaella Bernardi
Inspired by the literature on multisensory integration, we develop a computational model to ground quantifiers in perception.
1 code implementation • COLING 2018 • Hoa Trong Vu, Claudio Greco, Aliia Erofeeva, Somayeh Jafaritazehjan, Guido Linders, Marc Tanti, Alberto Testoni, Raffaella Bernardi, Albert Gatt
Capturing semantic relations between sentences, such as entailment, is a long-standing challenge for computational semantics.
Ranked #2 on Natural Language Inference on V-SNLI