以遷移學習改善深度神經網路模型於中文歌詞情緒辨識

Using Transfer Learning to Improve Deep Neural Networks for Lyrics Emotion Recognition in Chinese

廖家誼(Jia-Yi Liao) ； 林亞宣(Ya-Hsuan Lin) ； 林冠成(Kuan-Cheng Lin) ； 張家瑋(Jia-Wei Chang)

《中文計算語言學期刊》 26卷2期 (2021/12) Pp. 1-16

摘要

情緒是音樂資訊檢索中的重要屬性，目前深度學習方法已被廣泛用於自動音樂情緒辨識。音樂情緒辨識主要以歌曲情緒為主，部分研究關注英文歌詞，罕見對於中文歌詞情緒辨識的研究。本研究提出運用遷移式學習改善深度神經網路模型─BERT預訓練模型在中文歌詞的情緒分類任務上。實驗結果顯示，直接使用BERT對中文維度情緒語料庫建立中文情緒分類模型，對中文歌詞情緒分類僅有50%的準確度，若使用BERT對中文維度情緒字典與片語建立情緒分類模型再遷移至中文維度情緒語料庫，能達到71%的歌詞情緒分類準確度。

關鍵字

自然語言處理 ； 音樂情緒辨識 ； 遷移學習 ； 中文歌詞

並列摘要

Emotion is an important attribute in music information retrieval. Deep learning methods have been widely used in the automatic recognition of music emotion. Most of the studies focus on the audio data, the role of lyrics in music emotion classification remains under-appreciated. Due to the richness of English language resources, most previous studies were based on English lyrics but rarely in Chinese. This study proposes an approach without specific training for the Chinese lyrics emotional classification task: using transfer learning to improve deep neural networks, BERT pre-training model, for the emotion classification in Chinese lyrics. The experimental results show that directly using BERT to build an emotion classification model of CVAT only reach 50% of the classification accuracy. However, using BERT with transfer learning from CVAW, CVAP, to CVAT can achieve 71% classification accuracy.

並列關鍵字

Natural Language Processing ； Music Emotion Recognition ； Transfer learning ； Chinese Lyrics

參考文獻

Abdillah, J., Asror, I., & Wibowo, Y. F. A. (2020). Emotion classification of song lyrics using bidirectional lstm method with glove word representation weighting. Jurnal RESTI (Rekayasa Sistem Dan Teknologi Informasi), 4(4), 723-729. https://doi.org/10.29207/resti.v4i4.2156

Hung, J. C., Lin, K. C., & Lai, N. X. (2019). Recognizing learning emotion based on convolutional neural networks and transfer learning. Applied Soft Computing, 84, 105724. https://doi.org/10.1016/j.asoc.2019.105724

Hung, J. C., & Chang, J. W. (2021). Multi-level transfer learning for improving the performance of deep neural networks: Theory and practice from the tasks of facial emotion recognition and named entity recognition. Applied Soft Computing, 109, 107491. https://doi.org/10.1016/j.asoc.2021.107491

Malheiro, R., Panda, R., Gomes, P., & Paiva, R. P. (2016). Emotionally-relevant features for classification and regression of music lyrics. IEEE Transactions on Affective Computing, 9(2), 240-254. https://doi.org/10.1109/TAFFC.2016.2598569

Qiu, L., Chen, J., Ramsay, J., & Lu, J. (2019). Personality predicts words in favorite songs. Journal of Research in Personality, 78, 25-35. https://doi.org/10.1016/j.jrp.2018.11.004