Search Results for author: Giuseppe Serra

Found 27 papers, 12 papers with code

Keyphrase Generation with GANs in Low-Resources Scenarios

no code implementations EMNLP (sustainlp) 2020 Giuseppe Lancioni, Saida S.Mohamed, Beatrice Portelli, Giuseppe Serra, Carlo Tasso

Keyphrase Generation is the task of predicting Keyphrases (KPs), short phrases that summarize the semantic meaning of a given document.

Keyphrase Generation

Learning to Explain Graph Neural Networks

1 code implementation28 Sep 2022 Giuseppe Serra, Mathias Niepert

Graph Neural Networks (GNNs) are a popular class of machine learning models.

Increasing Adverse Drug Events extraction robustness on social media: case study on negation and speculation

no code implementations6 Sep 2022 Simone Scaboro, Beatrice Portelli, Emmanuele Chersoni, Enrico Santus, Giuseppe Serra

In the last decade, an increasing number of users have started reporting Adverse Drug Events (ADE) on social media platforms, blogs, and health forums.

A Feature-space Multimodal Data Augmentation Technique for Text-video Retrieval

1 code implementation3 Aug 2022 Alex Falcon, Giuseppe Serra, Oswald Lanz

Data augmentation techniques were introduced to increase the performance on unseen test examples by creating new training samples with the application of semantics-preserving techniques, such as color space or geometric transformations on images.

Data Augmentation Retrieval +1

Human-Centric Research for NLP: Towards a Definition and Guiding Questions

no code implementations10 Jul 2022 Bhushan Kotnis, Kiril Gashteovski, Julia Gastinger, Giuseppe Serra, Francesco Alesiani, Timo Sztyler, Ammar Shaker, Na Gong, Carolin Lawrence, Zhao Xu

With Human-Centric Research (HCR) we can steer research activities so that the research outcome is beneficial for human stakeholders, such as end users.

Relevance-based Margin for Contrastively-trained Video Retrieval Models

1 code implementation27 Apr 2022 Alex Falcon, Swathikiran Sudhakaran, Giuseppe Serra, Sergio Escalera, Oswald Lanz

We show that even if we carefully tuned the fixed margin, our technique (which does not have the margin as a hyper-parameter) would still achieve better performance.

Multi-Instance Retrieval Natural Language Queries +2

Learning video retrieval models with relevance-aware online mining

2 code implementations16 Mar 2022 Alex Falcon, Giuseppe Serra, Oswald Lanz

Due to the amount of videos and related captions uploaded every hour, deep learning-based solutions for cross-modal video retrieval are attracting more and more attention.

Multi-Instance Retrieval Retrieval +1

NADE: A Benchmark for Robust Adverse Drug Events Extraction in Face of Negations

1 code implementation WNUT (ACL) 2021 Simone Scaboro, Beatrice Portelli, Emmanuele Chersoni, Enrico Santus, Giuseppe Serra

Adverse Drug Event (ADE) extraction models can rapidly examine large collections of social media texts, detecting mentions of drug-related adverse reactions and trigger medical investigations.

Negation Detection

Can the Crowd Judge Truthfulness? A Longitudinal Study on Recent Misinformation about COVID-19

1 code implementation25 Jul 2021 Kevin Roitero, Michael Soprano, Beatrice Portelli, Massimiliano De Luise, Damiano Spina, Vincenzo Della Mea, Giuseppe Serra, Stefano Mizzaro, Gianluca Demartini

Our results show that: workers are able to detect and objectively categorize online (mis)information related to COVID-19; both crowdsourced and expert judgments can be transformed and aggregated to improve quality; worker background and other signals (e. g., source of information, behavior) impact the quality of the data.

Misinformation

Data augmentation techniques for the Video Question Answering task

no code implementations22 Aug 2020 Alex Falcon, Oswald Lanz, Giuseppe Serra

Video Question Answering (VideoQA) is a task that requires a model to analyze and understand both the visual content given by the input video and the textual part given by the question, and the interaction between them in order to produce a meaningful answer.

Data Augmentation Question Answering +1

The COVID-19 Infodemic: Can the Crowd Judge Recent Misinformation Objectively?

1 code implementation13 Aug 2020 Kevin Roitero, Michael Soprano, Beatrice Portelli, Damiano Spina, Vincenzo Della Mea, Giuseppe Serra, Stefano Mizzaro, Gianluca Demartini

Misinformation is an ever increasing problem that is difficult to solve for the research community and has a negative impact on the society at large.

Misinformation

Distilling the Evidence to Augment Fact Verification Models

no code implementations WS 2020 Beatrice Portelli, Jason Zhao, Tal Schuster, Giuseppe Serra, Enrico Santus

We propose, instead, a model-agnostic framework that consists of two modules: (1) a span extractor, which identifies the crucial information connecting claim and evidence; and (2) a classifier that combines claim, evidence, and the extracted spans to predict the veracity of the claim.

Fact Verification

Text-to-Image Synthesis Based on Machine Generated Captions

no code implementations9 Oct 2019 Marco Menardi, Alex Falcon, Saida S. Mohamed, Lorenzo Seidenari, Giuseppe Serra, Alberto del Bimbo, Carlo Tasso

To address this issue, in this paper we propose an approach capable of generating images starting from a given text using conditional GANs trained on uncaptioned images dataset.

Image Captioning Image Generation

Video-Based Convolutional Attention for Person Re-Identification

no code implementations26 Sep 2019 Marco Zamprogno, Marco Passon, Niki Martinel, Giuseppe Serra, Giuseppe Lancioni, Christian Micheloni, Carlo Tasso, Gian Luca Foresti

In this paper we consider the problem of video-based person re-identification, which is the task of associating videos of the same person captured by different and non-overlapping cameras.

Video-Based Person Re-Identification

Exploiting and Evaluating a Supervised, Multilanguage Keyphrase Extraction pipeline for under-resourced languages

no code implementations RANLP 2017 Marco Basaldella, Muhammad Helmy, Elisa Antolli, Mihai Horia Popescu, Giuseppe Serra, Carlo Tasso

On the five languages we analyzed, results show an improvement in performance when using a machine learning algorithm, even if such algorithm is not trained and tested on the same language.

BIG-bench Machine Learning Information Retrieval +2

Paying More Attention to Saliency: Image Captioning with Saliency and Context Attention

no code implementations26 Jun 2017 Marcella Cornia, Lorenzo Baraldi, Giuseppe Serra, Rita Cucchiara

Image captioning has been recently gaining a lot of attention thanks to the impressive achievements shown by deep captioning architectures, which combine Convolutional Neural Networks to extract image representations, and Recurrent Neural Networks to generate the corresponding captions.

Ranked #2 on Image Captioning on Flickr30k Captions test (using extra training data)

Image Captioning Saliency Prediction

Predicting Human Eye Fixations via an LSTM-based Saliency Attentive Model

1 code implementation29 Nov 2016 Marcella Cornia, Lorenzo Baraldi, Giuseppe Serra, Rita Cucchiara

Data-driven saliency has recently gained a lot of attention thanks to the use of Convolutional Neural Networks for predicting gaze fixations.

Saliency Prediction

A Deep Multi-Level Network for Saliency Prediction

2 code implementations5 Sep 2016 Marcella Cornia, Lorenzo Baraldi, Giuseppe Serra, Rita Cucchiara

Current state of the art models for saliency prediction employ Fully Convolutional networks that perform a non-linear combination of features extracted from the last convolutional layer to predict saliency maps.

Saliency Prediction

Video Registration in Egocentric Vision under Day and Night Illumination Changes

no code implementations28 Jul 2016 Stefano Alletto, Giuseppe Serra, Rita Cucchiara

To effectively register an egocentric video sequence under these conditions, we propose to tackle the source of the problem: the matching process.

A Data-Driven Approach for Tag Refinement and Localization in Web Videos

no code implementations2 Jul 2014 Lamberto Ballan, Marco Bertini, Giuseppe Serra, Alberto del Bimbo

Our approach exploits collective knowledge embedded in user-generated tags and web sources, and visual similarity of keyframes and images uploaded to social sites like YouTube and Flickr, as well as web sources like Google and Bing.

TAG

Cannot find the paper you are looking for? You can Submit a new open access paper.