Inducing Semantic Micro-Clusters from Deep Multi-View Representations of Novels

Lea Frermann, György Szarvas


Abstract
Automatically understanding the plot of novels is important both for informing literary scholarship and applications such as summarization or recommendation. Various models have addressed this task, but their evaluation has remained largely intrinsic and qualitative. Here, we propose a principled and scalable framework leveraging expert-provided semantic tags (e.g., mystery, pirates) to evaluate plot representations in an extrinsic fashion, assessing their ability to produce locally coherent groupings of novels (micro-clusters) in model space. We present a deep recurrent autoencoder model that learns richly structured multi-view plot representations, and show that they i) yield better micro-clusters than less structured representations; and ii) are interpretable, and thus useful for further literary analysis or labeling of the emerging micro-clusters.
Anthology ID:
D17-1200
Volume:
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
Month:
September
Year:
2017
Address:
Copenhagen, Denmark
Editors:
Martha Palmer, Rebecca Hwa, Sebastian Riedel
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
1873–1883
Language:
URL:
https://aclanthology.org/D17-1200
DOI:
10.18653/v1/D17-1200
Bibkey:
Cite (ACL):
Lea Frermann and György Szarvas. 2017. Inducing Semantic Micro-Clusters from Deep Multi-View Representations of Novels. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 1873–1883, Copenhagen, Denmark. Association for Computational Linguistics.
Cite (Informal):
Inducing Semantic Micro-Clusters from Deep Multi-View Representations of Novels (Frermann & Szarvas, EMNLP 2017)
Copy Citation:
PDF:
https://aclanthology.org/D17-1200.pdf
Attachment:
 D17-1200.Attachment.zip
Data
characterRelations