On exploiting transformers for detecting explicit song lyrics

被引:2
|
作者
Rospocher, Marco [1 ]
机构
[1] Univ Verona, Verona, Italy
关键词
Transformer-based language models; Convolutional neural networks; Text classification; Explicit content detection;
D O I
10.1016/j.entcom.2022.100508
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
Determining if the lyrics of a given song could be hurtful or inappropriate for children is of utmost importance to prevent the reproduction of songs whose textual content is unsuitable for them. This problem can be computationally tackled as a binary classification task, and in the last couple of years various machine learning approaches have been applied to perform this task automatically. In this work, we investigate the automatic detection of explicit song lyrics by leveraging transformer-based language models, i.e., large language representations, unsupervisely built from huge textual corpora, that can be fine-tuned on various natural language processing tasks, such as text classification. We assess the performance of various transformer-based language model classifiers on a dataset consisting of more than 800K lyrics, marked with explicit information. The evaluation shows that while the classifiers built with these powerful tools achieve state-of-the-art performance, they do not outperform lighter and computationally less demanding approaches. We complement this empirical evaluation with further analyses, including an assessment of the performance of these classifiers in a few-shot learning scenario, where they are trained with just few thousands of samples.
引用
收藏
页数:9
相关论文
共 50 条
  • [41] Translating Song. Lyrics and Texts
    Mateo, Marta
    [J]. JOURNAL OF SPECIALISED TRANSLATION, 2018, (29): : 273 - 275
  • [42] Decoding the Style and Bias of Song Lyrics
    Barman, Manash Pratim
    Awekar, Amit
    Kothari, Sambhav
    [J]. PROCEEDINGS OF THE 42ND INTERNATIONAL ACM SIGIR CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION RETRIEVAL (SIGIR '19), 2019, : 1165 - 1168
  • [43] Studying the vocabulary of reggaeton song lyrics
    Vankova, Pavlina
    [J]. TOPICS IN LINGUISTICS, 2022, 23 (02) : 63 - 88
  • [44] Singing and Accompaniment Support the Processing of Song Lyrics and Change the Lyrics' Meaning [1]
    Schotanus, Yke
    [J]. EMPIRICAL MUSICOLOGY REVIEW, 2020, 15 (1-2): : 18 - 55
  • [45] The Secret of Bill Monroe's Song Lyrics
    Pribylova, Irena
    [J]. OD FOLKLORU K WORLD MUSIC: HUDBA A SLOVO: Redigovaly Irena Pribylova a Lucie Uhlikova, 2022, : 127 - 140
  • [46] Song Lyrics of the 90's with Migration Background
    Balci, Umut
    [J]. SELCUK UNIVERSITESI EDEBIYAT FAKULTESI DERGISI-SELCUK UNIVERSITY JOURNAL OF FACULTY OF LETTERS, 2019, 41 : 193 - 208
  • [47] The Contemporary Czech Protest Song: Song Lyrics as a Mirror of the Agitated Society
    Tesar, Milan
    [J]. OD FOLKLORU K WORLD MUSIC: ZRCADLENI, 2017, : 198 - 208
  • [48] RETRIEVAL OF SONG LYRICS FROM SUNG QUERIES
    Kruspe, Anna M.
    Goto, Masataka
    [J]. 2018 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2018, : 111 - 115
  • [49] Ethnic and Cultural Identity in Music and Song Lyrics
    Skinner, Heather
    [J]. ARTS AND THE MARKET, 2018, 8 (01) : 113 - 114
  • [50] Automated Generation of Song Lyrics using CFGs
    Pudaruth, Sameerchand
    Amourdon, Sandiana
    Anseline, Joey
    [J]. 2014 SEVENTH INTERNATIONAL CONFERENCE ON CONTEMPORARY COMPUTING (IC3), 2014, : 613 - 616