no code implementations • NAACL (NLPMC) 2021 • Seyed Mahed Mousavi, Alessandra Cervone, Morena Danieli, Giuseppe Riccardi
The acquisition of a dialogue corpus is a key step in the process of training a dialogue model.
1 code implementation • WASSA (ACL) 2022 • Seyed Mahed Mousavi, Gabriel Roccabruna, Aniruddha Tammewar, Steve Azzolin, Giuseppe Riccardi
Deep Neural Networks (DNN) models have achieved acceptable performance in sentiment prediction of written text.
1 code implementation • 10 Apr 2024 • Seyed Mahed Mousavi, Simone Alghisi, Giuseppe Riccardi
We study the appropriateness of Large Language Models (LLMs) as knowledge repositories.
no code implementations • 4 Jan 2024 • Seyed Mahed Mousavi, Gabriel Roccabruna, Simone Alghisi, Massimo Rizzoli, Mirco Ravanelli, Giuseppe Riccardi
Large Pre-Trained Language Models have demonstrated state-of-the-art performance in different downstream tasks, including dialogue state tracking and end-to-end response generation.
no code implementations • 27 May 2023 • Gabriel Roccabruna, Seyed Mahed Mousavi, Giuseppe Riccardi
We further observed that the discriminative model achieves the best trade-off of valence and EC prediction tasks in the joint prediction setting.
no code implementations • 25 May 2023 • Seyed Mahed Mousavi, Simone Caldarella, Giuseppe Riccardi
Dialogue systems designed for LDs should uniquely interact with the users over multiple sessions and long periods of time (e. g. weeks), and engage them in personal dialogues to elaborate on their feelings, thoughts, and real-life events.
1 code implementation • 15 Feb 2023 • Seyed Mahed Mousavi, Shohei Tanaka, Gabriel Roccabruna, Koichiro Yoshino, Satoshi Nakamura, Giuseppe Riccardi
We publish the annotated dataset, annotation materials, and machine learning baseline models for the task of new event extraction for narrative understanding.