Search

Your search keyword '"Michael Fell"' showing total 6 results
Start Over Author "Michael Fell" Topic artificial intelligence
6 results on '"Michael Fell"'

1. EVALITA4ELG: Italian Benchmark Linguistic Resources, NLP Services and Tools for the ELG Platform

Author

Andrea Bolioli, Michael Fell, Viviana Patti, Rossella Varvara, Valerio Basile, Cristina Bosco, and Alessio Bosca

Subjects
European Language Grid platform, Italian, Language Grid, business.industry, Computer science, Interface (Java), NLP and evaluation, Social Sciences, EVALITA, General Medicine, computer.software_genre, Benchmark Linguistic Resources, Benchmark (computing), Computational linguistics. Natural language processing, Language technologies, Artificial intelligence, NLP services, Web service, P98-98.5, Benchmark Linguistic Resources, Italian, EVALITA, NLP and evaluation, European Language Grid platform, Language technologies, NLP services, business, computer, Natural language processing
Abstract

Starting from the first edition held in 2007, EVALITA is the initiative for the evaluation of Natural Language Processing tools for Italian. This paper describes the EVALITA4ELG project, whose main aim is at systematically collecting the resources released as benchmarks for this evaluation campaign, and making them easily accessible through the European Language Grid platform. The collection is moreover integrated with systems and baselines as a pool of web services with a common interface, deployed on a dedicated hardware infrastructure.

Published
2021

2. Should we be concerned about multiple comparisons in hierarchical Bayesian models?

Author

Drew M. P. Peltier, Jessica S. Guo, Kiona Ogle, Jarrett J. Barber, Heather Kropp, and Michael Fell

Subjects
business.industry, Computer science, Ecological Modeling, Bayesian probability, Familywise error rate, Machine learning, computer.software_genre, Hierarchical database model, Multiple comparisons problem, Artificial intelligence, business, computer, Ecology, Evolution, Behavior and Systematics, Type I and type II errors
Published
2019
Full Text
View/download PDF

3. Lyrics segmentation via bimodal text–audio representation

Author

Elena Cabrio, Fabien Gandon, Yaroslav Nechaev, Michael Fell, Geoffroy Peeters, Gabriel Meseguer-Brocal, Web-Instrumented Man-Machine Interactions, Communities and Semantics (WIMMICS), Inria Sophia Antipolis - Méditerranée (CRISAM), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Scalable and Pervasive softwARe and Knowledge Systems (Laboratoire I3S - SPARKS), Laboratoire d'Informatique, Signaux, et Systèmes de Sophia Antipolis (I3S), Université Nice Sophia Antipolis (1965 - 2019) (UNS), COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Centre National de la Recherche Scientifique (CNRS)-Université Côte d'Azur (UCA)-Université Nice Sophia Antipolis (1965 - 2019) (UNS), COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Centre National de la Recherche Scientifique (CNRS)-Université Côte d'Azur (UCA)-Laboratoire d'Informatique, Signaux, et Systèmes de Sophia Antipolis (I3S), COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Centre National de la Recherche Scientifique (CNRS)-Université Côte d'Azur (UCA), Amazon, Cambridge, MA, USA, Institut de Recherche et Coordination Acoustique/Musique (IRCAM), Sorbonne Université (SU), Centre National de la Recherche Scientifique (CNRS), Laboratoire Traitement et Communication de l'Information (LTCI), Institut Mines-Télécom [Paris] (IMT)-Télécom Paris, Université Nice Sophia Antipolis (... - 2019) (UNS), COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Centre National de la Recherche Scientifique (CNRS)-Université Côte d'Azur (UCA)-Université Nice Sophia Antipolis (... - 2019) (UNS), Fondazione Bruno Kessler [Trento, Italy] (FBK), Département Images, Données, Signal (IDS), Télécom ParisTech, Signal, Statistique et Apprentissage (S2A), Institut Mines-Télécom [Paris] (IMT)-Télécom Paris-Institut Mines-Télécom [Paris] (IMT)-Télécom Paris, and Institut Polytechnique de Paris (IP Paris)

Subjects
Structure (mathematical logic), Linguistics and Language, Computer science, Speech recognition, 02 engineering and technology, Processing Music, Lyrics, Convolutional neural network, Language and Linguistics, [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL], [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], Artificial Intelligence, Text Segmentation, Text structure, Information Retrieval, 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Segmentation, Representation (mathematics), Software, Natural Language, Natural Language in Multimodal and Multimedia Systems
Abstract

Song lyrics contain repeated patterns that have been proven to facilitate automated lyrics segmentation, with the final goal of detecting the building blocks (e.g., chorus, verse) of a song text. Our contribution in this article is twofold. First, we introduce a convolutional neural network (CNN)-based model that learns to segment the lyrics based on their repetitive text structure. We experiment with novel features to reveal different kinds of repetitions in the lyrics, for instance based on phonetical and syntactical properties. Second, using a novel corpus where the song text is synchronized to the audio of the song, we show that the text and audio modalities capture complementary structure of the lyrics and that combining both is beneficial for lyrics segmentation performance. For the purely text-based lyrics segmentation on a dataset of 103k lyrics, we achieve an F-score of 67.4%, improving on the state of the art (59.2% F-score). On the synchronized text–audio dataset of 4.8k songs, we show that the additional audio features improve segmentation performance to 75.3% F-score, significantly outperforming the purely text-based approaches.

Published
2021
Full Text
View/download PDF

4. Comparing Automated Methods to Detect Explicit Content in Song Lyrics

Author

Fabien Gandon, Michael Fell, Elena Cabrio, Michele Corazza, Michael Fell, Elena Cabrio, Michele Corazza, Fabien Gandon, Laboratoire d'Informatique, Signaux, et Systèmes de Sophia Antipolis (I3S), Université Nice Sophia Antipolis (... - 2019) (UNS), COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Centre National de la Recherche Scientifique (CNRS)-Université Côte d'Azur (UCA), Web-Instrumented Man-Machine Interactions, Communities and Semantics (WIMMICS), Inria Sophia Antipolis - Méditerranée (CRISAM), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Scalable and Pervasive softwARe and Knowledge Systems (Laboratoire I3S - SPARKS), COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Centre National de la Recherche Scientifique (CNRS)-Université Côte d'Azur (UCA)-Université Nice Sophia Antipolis (... - 2019) (UNS), COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Centre National de la Recherche Scientifique (CNRS)-Université Côte d'Azur (UCA)-Laboratoire d'Informatique, Signaux, et Systèmes de Sophia Antipolis (I3S), ANR-16-CE23-0017,WASABI,Web Audio et Web Sémantique agrégées dans le navigateur pour de l'indexation(2016), Université Nice Sophia Antipolis (1965 - 2019) (UNS), and COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Centre National de la Recherche Scientifique (CNRS)-Université Côte d'Azur (UCA)-Université Nice Sophia Antipolis (1965 - 2019) (UNS)

Subjects
education.field_of_study, business.industry, Computer science, 05 social sciences, 010501 environmental sciences, Lyrics, computer.software_genre, 01 natural sciences, [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL], Task (project management), [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], Qualitative analysis, 0502 economics and business, Deep neural networks, Warning label, [INFO]Computer Science [cs], Artificial intelligence, 050207 economics, business, education, computer, Natural language processing, Natural language processing, Machine learning, Explicit lyrics detection, 0105 earth and related environmental sciences
Abstract

International audience; The Parental Advisory Label (PAL) is a warning label that is placed on audio recordings inrecognition of profanity or inappropriate references, with the intention of alerting parents of material potentially unsuitable for children.Since 2015, digital providers – such as iTunes,Spotify, Amazon Music and Deezer – also follow PAL guidelines and tag such tracks as “explicit”. Nowadays, such labelling is carried out mainly manually on voluntary basis, with the drawbacks of being time consuming and therefore costly, error prone and partly a subjective task. In this paper, we compare auto-mated methods ranging from dictionary-basedlookup to state-of-the-art deep neural networks to automatically detect explicit contents in English lyrics. We show that more complex models perform only slightly better on this task, and relying on a qualitative analysis of thedata, we discuss the inherent hardness and subjectivity of the task.

Published
2019

5. Song Lyrics Summarization Inspired by Audio Thumbnailing

Author

Fabien Gandon, Alain Giboin, Elena Cabrio, Michael Fell, Web-Instrumented Man-Machine Interactions, Communities and Semantics (WIMMICS), Inria Sophia Antipolis - Méditerranée (CRISAM), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Scalable and Pervasive softwARe and Knowledge Systems (Laboratoire I3S - SPARKS), Laboratoire d'Informatique, Signaux, et Systèmes de Sophia Antipolis (I3S), Université Nice Sophia Antipolis (... - 2019) (UNS), COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Centre National de la Recherche Scientifique (CNRS)-Université Côte d'Azur (UCA)-Université Nice Sophia Antipolis (... - 2019) (UNS), COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Centre National de la Recherche Scientifique (CNRS)-Université Côte d'Azur (UCA)-Laboratoire d'Informatique, Signaux, et Systèmes de Sophia Antipolis (I3S), COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Centre National de la Recherche Scientifique (CNRS)-Université Côte d'Azur (UCA), Université Nice Sophia Antipolis (1965 - 2019) (UNS), and COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Centre National de la Recherche Scientifique (CNRS)-Université Côte d'Azur (UCA)-Université Nice Sophia Antipolis (1965 - 2019) (UNS)

Subjects
Structure (mathematical logic), Computer science, business.industry, InformationSystems_INFORMATIONSTORAGEANDRETRIEVAL, Thumbnail, 02 engineering and technology, Lyrics, computer.software_genre, Automatic summarization, [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL], [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], 020204 information systems, ComputingMethodologies_DOCUMENTANDTEXTPROCESSING, 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, [INFO]Computer Science [cs], Artificial intelligence, business, computer, Natural language processing, ComputingMilieux_MISCELLANEOUS
Abstract

Given the peculiar structure of songs, applying generic text summarization methods to lyrics can lead to the generation of highly redundant and incoherent text. In this paper, we propose to enhance state-of-the-art text summarization approaches with a method inspired by audio thumbnailing. Instead of searching for the thumbnail clues in the audio of the song, we identify equivalent clues in the lyrics. We then show how these summaries that take into account the audio nature of the lyrics outperform the generic methods according to both an automatic evaluation and human judgments.

Published
2019

6. An Ensemble Approach of Recurrent Neural Networks using Pre-Trained Embeddings for Playlist Completion

Author

Elena Cabrio, Pasquale Lisena, Giuseppe Rizzo, Michael Fell, Enrico Palumbo, Diego Monti, Raphaël Troncy, and Maurizio Morisio

Subjects
business.industry, Computer science, InformationSystems_INFORMATIONINTERFACESANDPRESENTATION(e.g.,HCI), Recommender, Ensemble, RNN, Embeddings, RecSys Challenge, RecSys Challenge, Statistical model, 02 engineering and technology, Recommender system, Machine learning, computer.software_genre, RNN, Task (project management), Embeddings, Set (abstract data type), Recurrent neural network, Recommender, 020204 information systems, 0202 electrical engineering, electronic engineering, information engineering, Training phase, 020201 artificial intelligence & image processing, Artificial intelligence, Ensemble strategy, business, computer, Ensemble
Abstract

This paper describes the approach of the D2KLab team to the RecSys Challenge 2018 that focuses on the task of playlist completion. We propose an ensemble strategy of different recurrent neural networks leveraging pre-trained embeddings representing tracks, artists, albums, and titles as inputs. We also use lyrics from which we extract semantic and stylistic features that we fed into the network for the creative track. The RNN learns a probabilistic model from the sequences of items in the playlist, which is then used to predict the most likely tracks to be added to the playlist. Concerning the playlists without tracks, we implemented a fall-back strategy called Title2Rec that generates recommendations using only the playlist title. We optimized the RNN, Title2Rec, and the ensemble approach on a validation set, tuning hyper-parameters such as the optimizer algorithm, the learning rate, and the generation strategy. This approach is effective in predicting tracks for a playlist and flexible to include diverse types of inputs, but it is also computationally demanding in the training phase.

Published
2018
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results