AIConfPaper
← Search

Paolo Rosso

9 accepted papers

2025

“Stupid robot, I want to speak to a human!” User Frustration Detection in Task-Oriented Dialog Systems

Mireia Hernandez Caralt, Ivan Sekulic, Filip Carevic, Nghia Khau, Diana Nicoleta Popa, Bruna Guedes +6
COLING 2025industry

Detecting user frustration in modern-day task-oriented dialog (TOD) systems is imperative for maintaining overall user satisfaction, engagement, and retention. However, most recent research is focused on sentiment and emotion detection in academic settings, thus failing to fully encapsulate implicat…

Cited by 0Source ↗PDF ↗Scholar ↗
2024

RoCode: A Dataset for Measuring Code Intelligence from Problem Definitions in Romanian

Adrian Cosma, Ioan-Bogdan Iordache, Paolo Rosso
COLING 2024main

Recently, large language models (LLMs) have become increasingly powerful and have become capable of solving a plethora of tasks through proper instructions in natural language. However, the vast majority of testing suites assume that the instructions are written in English, the de facto prompting la…

Cited by 3Source ↗PDF ↗code ↗Scholar ↗
2023

Definitions Matter: Guiding GPT for Multi-label Classification

Youri Peskine, Damir Korenčić, Ivan Grubisic, Paolo Papotti, Raphael Troncy, Paolo Rosso
EMNLP 2023short findings

Large language models have recently risen in popularity due to their ability to perform many natural language tasks without requiring any fine-tuning. In this work, we focus on two novel ideas: (1) generating definitions from examples and using them for zero-shot classification, and (2) investigatin…

Cited by 0Source ↗Scholar ↗
2023

Vicinal Risk Minimization for Few-Shot Cross-lingual Transfer in Abusive Language Detection

Gretel Liz De la Peña Sarracén, Paolo Rosso, Robert Litschko, Goran Glavaš, Simone Paolo Ponzetto
EMNLP 2023long main

Cross-lingual transfer learning from high-resource to medium and low-resource languages has shown encouraging results. However, the scarcity of resources in target languages remains a challenge. In this work, we resort to data augmentation and continual pre-training for domain adaptation to improve…

Cited by 0Source ↗Scholar ↗
2023

Zero-Shot Data Maps. Efficient Dataset Cartography Without Model Training

Angelo Basile, Marc Franco-Salvador, Paolo Rosso
EMNLP 2023long findings

Data Maps (Swayamdipta, et al. 2020) have emerged as a powerful tool for diagnosing large annotated datasets. Given a model fitted on a dataset, these maps show each data instance from the dataset in a 2-dimensional space defined by a) the model's confidence in the true class and b) the variability…

Cited by 0Source ↗code ↗Scholar ↗
2022

Cryptocurrency Bubble Detection: A New Stock Market Dataset, Financial Task & Hyperbolic Models

Ramit Sawhney, Shivam Agarwal, Vivek Mittal, Paolo Rosso, Vikram Nanda, Sudheer Chava
NAACL 2022long

The rapid spread of information over social media influences quantitative trading and investments. The growing popularity of speculative trading of highly volatile assets such as cryptocurrencies and meme stocks presents a fresh challenge in the financial realm. Investigating such “bubbles” - period…

Cited by 24Source ↗PDF ↗code ↗Scholar ↗
2020

Location Prediction over Sparse User Mobility Traces Using RNNs: Flashback in Hidden States!

Dingqi Yang, Benjamin Fankhauser, Paolo Rosso, Philippe Cudre-Mauroux
IJCAI 2020poster

Location prediction is a key problem in human mobility modeling, which predicts a user's next location based on historical user mobility traces. As a sequential prediction problem by nature, it has been recently studied using Recurrent Neural Networks (RNNs). Due to the sparsity of user mobility tra…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2020

Multilingual Irony Detection with Dependency Syntax and Neural Models

Alessandra Teresa Cignarella, Valerio Basile, Manuela Sanguinetti, Cristina Bosco, Paolo Rosso, Farah Benamara
COLING 2020main

This paper presents an in-depth investigation of the effectiveness of dependency-based syntactic features on the irony detection task in a multilingual perspective (English, Spanish, French and Italian). It focuses on the contribution from syntactic knowledge, exploiting linguistic resources where s…

Cited by 26Source ↗PDF ↗code ↗Scholar ↗