Zobrazeno 1 - 10
of 65
pro vyhledávání: '"Keller, Mikaela"'
Byte-Pair Encoding (BPE) is an algorithm commonly used in Natural Language Processing to build a vocabulary of subwords, which has been recently applied to symbolic music. Given that symbolic music can differ significantly from text, particularly wit
Externí odkaz:
http://arxiv.org/abs/2410.01448
In this paper, we introduce a data augmentation approach specifically tailored to enhance intersectional fairness in classification tasks. Our method capitalizes on the hierarchical structure inherent to intersectionality, by viewing groups as inters
Externí odkaz:
http://arxiv.org/abs/2405.14521
Several adaptations of Transformers models have been developed in various domains since its breakthrough in Natural Language Processing (NLP). This trend has spread into the field of Music Information Retrieval (MIR), including studies processing mus
Externí odkaz:
http://arxiv.org/abs/2402.17467
Lexical Semantic Change is the study of how the meaning of words evolves through time. Another related question is whether and how lexical relations over pairs of words, such as synonymy, change over time. There are currently two competing, apparentl
Externí odkaz:
http://arxiv.org/abs/2305.19143
In this work, we consider the problem of intersectional group fairness in the classification setting, where the objective is to learn discrimination-free models in the presence of several intersecting sensitive groups. First, we illustrate various sh
Externí odkaz:
http://arxiv.org/abs/2305.12495
Encoded text representations often capture sensitive attributes about individuals (e.g., race or gender), which raise privacy concerns and can make downstream models unfair to certain groups. In this work, we propose FEDERATE, an approach that combin
Externí odkaz:
http://arxiv.org/abs/2205.06135
Autor:
Wauquier, Pauline, Keller, Mikaela
The efficiency of graph-based semi-supervised algorithms depends on the graph of instances on which they are applied. The instances are often in a vectorial form before a graph linking them is built. The construction of the graph relies on a metric o
Externí odkaz:
http://arxiv.org/abs/1511.05789
Generative models for graphs have been typically committed to strong prior assumptions concerning the form of the modeled distributions. Moreover, the vast majority of currently available models are either only suitable for characterizing some partic
Externí odkaz:
http://arxiv.org/abs/1210.4860
In this work, we tackle the problem of intersectional group fairness in the classification setting, where the objective is to learn discrimination-free models in the presence of several intersecting sensitive groups. First, we illustrate various shor
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7e78f9d6c4d5052746c367c89b5017f0
http://arxiv.org/abs/2305.12495
http://arxiv.org/abs/2305.12495
Publikováno v:
23rd International Society for Music Information Retrieval Conference (ISMIR 2022), Late-Breaking Demo Session
23rd International Society for Music Information Retrieval Conference (ISMIR 2022), Late-Breaking Demo Session, Dec 2022, Bangaluru, India.
23rd International Society for Music Information Retrieval Conference (ISMIR 2022), Late-Breaking Demo Session, Dec 2022, Bangaluru, India.
International audience; Training sequence models such as transformers with symbolic music requires a representation of music as sequences of atomic elements called tokens. State-of-the-art music tokenizations encode pitch values explicitly, which com
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::58eaa1744ce418a26c0d98579c87334b
https://hal.science/hal-03877642/document
https://hal.science/hal-03877642/document