TY - JOUR
T1 - Searching for musical features using natural language queries
T2 - the C@merata evaluations at MediaEval
AU - Sutcliffe, Richard
AU - Hovy, Eduard
AU - Collins, Tom
AU - Wan, Stephen
AU - Crawford, Tim
AU - Root, Deane L.
N1 - Publisher Copyright:
© 2018, Springer Nature B.V.
PY - 2019/3/15
Y1 - 2019/3/15
N2 - Musicological texts about classical music frequently include detailed technical discussions concerning the works being analysed. These references can be specific (e.g. C sharp in the treble clef) or general (fugal passage, Thor’s Hammer). Experts can usually identify the features in question in music scores but a means of performing this task automatically could be very useful for experts and beginners alike. Following work on textual question answering over many years as co-organisers of the QA tasks at the Cross Language Evaluation Forum, we decided in 2013 to propose a new type of task where the input would be a natural language phrase, together with a music score in MusicXML, and the required output would be one or more matching passages in the score. We report here on 3 years of the C@merata task at MediaEval. We describe the design of the task, the evaluation methods we devised for it, the approaches adopted by participant systems and the results obtained. Finally, we assess the progress which has been made in aligning natural language text with music and map out the main steps for the future. The novel aspects of this work are: (1) the task itself, linking musical references to actual music scores, (2) the evaluation methods we devised, based on modified versions of precision and recall, applied to demarcated musical passages, and (3) the progress which has been made in analysing and interpreting detailed technical references to music within texts.
AB - Musicological texts about classical music frequently include detailed technical discussions concerning the works being analysed. These references can be specific (e.g. C sharp in the treble clef) or general (fugal passage, Thor’s Hammer). Experts can usually identify the features in question in music scores but a means of performing this task automatically could be very useful for experts and beginners alike. Following work on textual question answering over many years as co-organisers of the QA tasks at the Cross Language Evaluation Forum, we decided in 2013 to propose a new type of task where the input would be a natural language phrase, together with a music score in MusicXML, and the required output would be one or more matching passages in the score. We report here on 3 years of the C@merata task at MediaEval. We describe the design of the task, the evaluation methods we devised for it, the approaches adopted by participant systems and the results obtained. Finally, we assess the progress which has been made in aligning natural language text with music and map out the main steps for the future. The novel aspects of this work are: (1) the task itself, linking musical references to actual music scores, (2) the evaluation methods we devised, based on modified versions of precision and recall, applied to demarcated musical passages, and (3) the progress which has been made in analysing and interpreting detailed technical references to music within texts.
KW - Evaluation
KW - Music information retrieval
KW - MusicXML
KW - Musicological analysis
KW - Natural language processing
KW - Question answering
UR - http://www.scopus.com/inward/record.url?scp=85052109248&partnerID=8YFLogxK
U2 - 10.1007/s10579-018-9422-2
DO - 10.1007/s10579-018-9422-2
M3 - Article
AN - SCOPUS:85052109248
SN - 1574-020X
VL - 53
SP - 87
EP - 140
JO - Language Resources and Evaluation
JF - Language Resources and Evaluation
IS - 1
ER -