Break it Down for Me: A Study in Automated Lyric Annotation
This work addresses the problem of interpreting creative texts like song lyrics for readers, though it is incremental as it builds on existing text simplification and annotation methods.
The paper tackles the challenge of understanding ambiguous and jargon-filled lyrics by introducing the automated lyric annotation (ALA) task, which rephrases and clarifies song lyrics, and releases a crowdsourced dataset for it, finding that translation and retrieval models each capture unique information important for the task.
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.