Lotte and Annette: A Framework for Finding and Exploring Key Passages in Literary Works

Frederik Arnold, Robert Jäschke


Abstract
We present an approach that leverages expert knowledge contained in scholarly works to automatically identify key passages in literary works. Specifically, we extend a text reuse detection method for finding quotations, such that our system Lotte can deal with common properties of quotations, for example, ellipses or inaccurate quotations. An evaluation shows that Lotte outperforms four existing approaches. To generate key passages, we combine overlapping quotations from multiple scholarly texts. An interactive website, called Annette, for visualizing and exploring key passages makes the results accessible and explorable.
Anthology ID:
2021.nlp4dh-1.7
Volume:
Proceedings of the Workshop on Natural Language Processing for Digital Humanities
Month:
December
Year:
2021
Address:
NIT Silchar, India
Editors:
Mika Hämäläinen, Khalid Alnajjar, Niko Partanen, Jack Rueter
Venue:
NLP4DH
SIG:
Publisher:
NLP Association of India (NLPAI)
Note:
Pages:
55–63
Language:
URL:
https://aclanthology.org/2021.nlp4dh-1.7
DOI:
Bibkey:
Cite (ACL):
Frederik Arnold and Robert Jäschke. 2021. Lotte and Annette: A Framework for Finding and Exploring Key Passages in Literary Works. In Proceedings of the Workshop on Natural Language Processing for Digital Humanities, pages 55–63, NIT Silchar, India. NLP Association of India (NLPAI).
Cite (Informal):
Lotte and Annette: A Framework for Finding and Exploring Key Passages in Literary Works (Arnold & Jäschke, NLP4DH 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.nlp4dh-1.7.pdf