Story Trees: Representing Documents using Topological Persistence

Pantea Haghighatkhah, Antske Fokkens, Pia Sommerauer, Bettina Speckmann, Kevin Verbeek


Abstract
Topological Data Analysis (TDA) focuses on the inherent shape of (spatial) data. As such, it may provide useful methods to explore spatial representations of linguistic data (embeddings) which have become central in NLP. In this paper we aim to introduce TDA to researchers in language technology. We use TDA to represent document structure as so-called story trees. Story trees are hierarchical representations created from semantic vector representations of sentences via persistent homology. They can be used to identify and clearly visualize prominent components of a story line. We showcase their potential by using story trees to create extractive summaries for news stories.
Anthology ID:
2022.lrec-1.258
Volume:
Proceedings of the Thirteenth Language Resources and Evaluation Conference
Month:
June
Year:
2022
Address:
Marseille, France
Editors:
Nicoletta Calzolari, Frédéric Béchet, Philippe Blache, Khalid Choukri, Christopher Cieri, Thierry Declerck, Sara Goggi, Hitoshi Isahara, Bente Maegaard, Joseph Mariani, Hélène Mazo, Jan Odijk, Stelios Piperidis
Venue:
LREC
SIG:
Publisher:
European Language Resources Association
Note:
Pages:
2413–2429
Language:
URL:
https://aclanthology.org/2022.lrec-1.258
DOI:
Bibkey:
Cite (ACL):
Pantea Haghighatkhah, Antske Fokkens, Pia Sommerauer, Bettina Speckmann, and Kevin Verbeek. 2022. Story Trees: Representing Documents using Topological Persistence. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 2413–2429, Marseille, France. European Language Resources Association.
Cite (Informal):
Story Trees: Representing Documents using Topological Persistence (Haghighatkhah et al., LREC 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-2/2022.lrec-1.258.pdf