activity
20212023
most citedSimple LLM Prompting is State-of-the-Art for Robust and Multilingual Dialogue Evaluation

6 citations · 12 across the 5 of their papers we have counts for

collaborators

6 papers

cs.CL2023

Fuzzy Fingerprinting Transformer Language-Models for Emotion Recognition in Conversations

Patrícia Pereira, Rui Ribeiro, Helena Moniz +2

Fuzzy Fingerprints have been successfully used as an interpretable text classification technique, but, like most other techniques, have been largely surpassed in performance by Lar…

cs.CL2023★ 6 cited

Simple LLM Prompting is State-of-the-Art for Robust and Multilingual Dialogue Evaluation

John Mendonça, Patrícia Pereira, Helena Moniz +3

Despite significant research effort in the development of automatic dialogue evaluation metrics, little thought is given to evaluating dialogues other than in English. At the same…

cs.CL2023

Context-Dependent Embedding Utterance Representations for Emotion Recognition in Conversations

Patrícia Pereira, Helena Moniz, Isabel Dias +1

Emotion Recognition in Conversations (ERC) has been gaining increasing importance as conversational agents become more and more common. Recognizing emotions is key for effective co…

cs.CL2023

PGTask: Introducing the Task of Profile Generation from Dialogues

Rui Ribeiro, Joao P. Carvalho, Luísa Coheur

Recent approaches have attempted to personalize dialogue systems by leveraging profile information into models. However, this knowledge is scarce and difficult to obtain, which mak…

cs.CL2022★ 6 cited

Deep Emotion Recognition in Textual Conversations: A Survey

Patrícia Pereira, Helena Moniz, Joao Paulo Carvalho

Emotion Recognition in Conversations (ERC) is a key step towards successful human-machine interaction. While the field has seen tremendous advancement in the last few years, new ap…

cs.CL2021

Retrieval Augmentation for Deep Neural Networks

Rita Parada Ramos, Patrícia Pereira, Helena Moniz +2

Deep neural networks have achieved state-of-the-art results in various vision and/or language tasks. Despite the use of large training datasets, most models are trained by iteratin…