A Multi-task Framework with Enhanced Hierarchical Attention for Sentiment Analysis on Classical Chinese Poetry: Utilizing Information from Short Lines

Publication type
U
Publication status
Published
Authors
Du, Q, & Hoste, V.
Editor
Mika Hämäläinen, Emily Öhman, So Miyagawa, Khalid Alnajjar and Yuri Bizzoni
Series
Proceedings of the 4th International Conference on Natural Language Processing for Digital Humanities
Pagination
113-122
Publisher
Association for Computational Linguistics (Miami, USA)
Conference
The 4th International Conference on Natural Language Processing for Digital Humanities – NLP4DH 2024 (Miami, USA)
Download
(.pdf)
View in Biblio
(externe link)

Abstract

Classical Chinese poetry has a long history, dating back to the 11th century BC. By investigating the sentiment expressed in the poetry, we can gain more insights in the emotional life and history development in ancient Chinese culture. To help improve the sentiment analysis performance in the field of classical Chinese poetry, we propose to utilize the unique information from the individual short lines that compose the poem, and introduce a multi-task framework with hierarchical attention enhanced with short line sentiment labels. Specifically, the multi-task framework comprises sentiment analysis for both the overall poem and the short lines, while the hierarchical attention consists of word- and sentence-level attention, with the latter enhanced with additional information from short line sentiments. Our experimental results showcase that our approach leveraging more fine-grained information from short lines outperforms the state-of-the-art, achieving an accuracy score of 72.88% and an F1-macro score of 71.05%.