K-pop Lyric Translation: Dataset, Analysis, and Neural-Modelling

• URL: http://arxiv.org/abs/2309.11093v4
• Date: Sat, 18 May 2024 00:03:43 GMT
• Title: K-pop Lyric Translation: Dataset, Analysis, and Neural-Modelling
• Authors: Haven Kim, Jongmin Jung, Dasaem Jeong, Juhan Nam,
• Abstract summary: We introduce a novel singable lyric translation dataset, approximately 89% of which consists of K-pop song lyrics. This dataset aligns Korean and English lyrics line-by-line and section-by-section. We construct a neural lyric translation model, thereby underscoring the importance of a dedicated dataset for singable lyric translations.
• Score: 7.819710421921816
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Lyric translation, a field studied for over a century, is now attracting computational linguistics researchers. We identified two limitations in previous studies. Firstly, lyric translation studies have predominantly focused on Western genres and languages, with no previous study centering on K-pop despite its popularity. Second, the field of lyric translation suffers from a lack of publicly available datasets; to the best of our knowledge, no such dataset exists. To broaden the scope of genres and languages in lyric translation studies, we introduce a novel singable lyric translation dataset, approximately 89\% of which consists of K-pop song lyrics. This dataset aligns Korean and English lyrics line-by-line and section-by-section. We leveraged this dataset to unveil unique characteristics of K-pop lyric translation, distinguishing it from other extensively studied genres, and to construct a neural lyric translation model, thereby underscoring the importance of a dedicated dataset for singable lyric translations.

Related papers

• SongSage: A Large Musical Language Model with Lyric Generative Pre-training [69.52790104805794]
  SongSage is a large musical language model equipped with diverse lyric-centric intelligence through lyric generative pretraining.<n>SongSage exhibits a strong understanding of lyric-centric knowledge, excels in rewriting user queries for zero-shot playlist recommendations, generates and continues lyrics effectively, and performs proficiently across seven additional capabilities.
  arXiv  Detail & Related papers  (2026-01-03T10:54:37Z)
• LyCon: Lyrics Reconstruction from the Bag-of-Words Using Large Language Models [1.1510009152620668]
  Our study introduces a novel method for generating copyright-free lyrics from publicly available Bag-of-Words datasets. We have compiled and made available a dataset of reconstructed lyrics, LyCon, aligned with metadata from renowned sources. We believe that the integration of metadata such as mood annotations or genres enables a variety of academic experiments on lyrics.
  arXiv  Detail & Related papers  (2024-08-27T03:01:48Z)
• Decoupled Vocabulary Learning Enables Zero-Shot Translation from Unseen Languages [55.157295899188476]
  neural machine translation systems learn to map sentences of different languages into a common representation space. In this work, we test this hypothesis by zero-shot translating from unseen languages. We demonstrate that this setup enables zero-shot translation from entirely unseen languages.
  arXiv  Detail & Related papers  (2024-08-05T07:58:58Z)
• KpopMT: Translation Dataset with Terminology for Kpop Fandom [5.464669506214195]
  Expert translators provide 1k English translations for Korean posts and comments. We evaluate existing translation systems including GPT models on KpopMT to identify their failure cases.
  arXiv  Detail & Related papers  (2024-07-10T07:14:51Z)
• Synthetic Lyrics Detection Across Languages and Genres [4.987546582439803]
  Large language models (LLMs) to generate music content, particularly lyrics, has gained in popularity. Previous research has explored content detection in various domains, but no work has focused on the text modality, lyrics, in music. We curated a diverse dataset of real and synthetic lyrics from multiple languages, music genres, and artists. We performed a thorough evaluation of existing synthetic text detection approaches on lyrics, a previously unexplored data type. Following both music and industrial constraints, we examined how well these approaches generalize across languages, scale with data availability, handle multilingual language content, and perform on novel genres in few-shot settings
  arXiv  Detail & Related papers  (2024-06-21T15:19:21Z)
• The First Swahili Language Scene Text Detection and Recognition Dataset [55.83178123785643]
  There is a significant gap in low-resource languages, especially the Swahili Language. Swahili is widely spoken in East African countries but is still an under-explored language in scene text recognition. We propose a comprehensive dataset of Swahili scene text images and evaluate the dataset on different scene text detection and recognition models.
  arXiv  Detail & Related papers  (2024-05-19T03:55:02Z)
• A Computational Evaluation Framework for Singable Lyric Translation [17.492053233802135]
  We present a computational framework for the quantitative evaluation of singable lyric translation. We measure syllable count distance, phoneme repetition similarity, musical structure distance, and semantic similarity. Our framework seamlessly integrates musical, linguistic, and cultural dimensions of lyrics.
  arXiv  Detail & Related papers  (2023-08-26T00:27:08Z)
• Translate the Beauty in Songs: Jointly Learning to Align Melody and Translate Lyrics [38.35809268026605]
  We propose Lyrics-Melody Translation with Adaptive Grouping (LTAG) as a holistic solution to automatic song translation. It is a novel encoder-decoder framework that can simultaneously translate the source lyrics and determine the number of aligned notes at each decoding step. Experiments conducted on an English-Chinese song translation data set show the effectiveness of our model in both automatic and human evaluation.
  arXiv  Detail & Related papers  (2023-03-28T03:17:59Z)
• Speech-to-Speech Translation For A Real-world Unwritten Language [62.414304258701804]
  We study speech-to-speech translation (S2ST) that translates speech from one language into another language. We present an end-to-end solution from training data collection, modeling choices to benchmark dataset release.
  arXiv  Detail & Related papers  (2022-11-11T20:21:38Z)
• Analyzing the Use of Character-Level Translation with Sparse and Noisy Datasets [20.50917929755389]
  We find that character-level models cut the number of untranslated words by over 40% when applied to sparse and noisy datasets. We explore the impact of character alignment, phrase table filtering, bitext size and the choice of pivot language on translation quality. Neither word-nor character-BLEU correlate perfectly with human judgments, due to BLEU's sensitivity to length.
  arXiv  Detail & Related papers  (2021-09-27T07:35:47Z)
• ChrEnTranslate: Cherokee-English Machine Translation Demo with Quality Estimation and Corrective Feedback [70.5469946314539]
  ChrEnTranslate is an online machine translation demonstration system for translation between English and an endangered language Cherokee. It supports both statistical and neural translation models as well as provides quality estimation to inform users of reliability.
  arXiv  Detail & Related papers  (2021-07-30T17:58:54Z)
• CCPM: A Chinese Classical Poetry Matching Dataset [50.90794811956129]
  We propose a novel task to assess a model's semantic understanding of poetry by poem matching. This task requires the model to select one line of Chinese classical poetry among four candidates according to the modern Chinese translation of a line of poetry. To construct this dataset, we first obtain a set of parallel data of Chinese classical poetry and modern Chinese translation.
  arXiv  Detail & Related papers  (2021-06-03T16:49:03Z)
• Translation Artifacts in Cross-lingual Transfer Learning [51.66536640084888]
  We show that machine translation can introduce subtle artifacts that have a notable impact in existing cross-lingual models. In natural language inference, translating the premise and the hypothesis independently can reduce the lexical overlap between them. We also improve the state-of-the-art in XNLI for the translate-test and zero-shot approaches by 4.3 and 2.8 points, respectively.
  arXiv  Detail & Related papers  (2020-04-09T17:54:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.