arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1708.03492cs.CL
收藏

Break it Down for Me:自动歌词注释研究

Break it Down for Me: A Study in Automated Lyric Annotation

Language Technology Lab, DTAL, University of Cambridge(剑桥大学语言技术实验室);Department of Engineering, University of Cambridge(剑桥大学工程系);IDLab, Ghent University - imec(根特大学-imec IDLab)

Lucas Sterckx, Jason Naradowsky, Bill Byrne, Thomas Demeester, Chris Develder

摘要:

理解歌曲和诗歌中的歌词,对人类和机器读者都是一个挑战。这激发了对系统的需求,该系统可以理解在这种创造性文本中发现的歧义和行话,并提供注释以帮助读者达到正确的解释。我们介绍了自动歌词标注(ALA)的任务。像文本简化一样,ALA的目标是以更容易理解的方式重新表述原始文本。然而,在ALA中,系统必须经常包括额外的信息,以澄清利基术语和抽象概念。为了刺激对这项任务的研究,我们发布了大量的歌词众包注释。我们分析了翻译和检索模型在此任务上的性能,并通过自动和人工评估来衡量性能。我们发现,每个模型捕捉到一个独特的信息类型的重要任务。

英文摘要:

Comprehending lyrics, as found in songs and poems, can pose a challenge to human and machine readers alike. This motivates the need for systems that can understand the ambiguity and jargon found in such creative texts, and provide commentary to aid readers in reaching the correct interpretation. We introduce the task of automated lyric annotation (ALA). Like text simplification, a goal of ALA is to rephrase the original text in a more easily understandable manner. However, in ALA the system must often include additional information to clarify niche terminology and abstract concepts. To stimulate research on this task, we release a large collection of crowdsourced annotations for song lyrics. We analyze the performance of translation and retrieval models on this task, measuring performance with both automated and human evaluation. We find that each model captures a unique type of information important to the task.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑