Sig-Networks Toolkit: Signature Networks for Longitudinal Language Modelling

Talia Tseriotou, Ryan Chan, Adam Tsakalidis, Iman Munire Bilal, Elena Kochkina, Terry Lyons, Maria Liakata

Abstract
We present an open-source, pip installable toolkit, Sig-Networks, the first of its kind for longitudinal language modelling. A central focus is the incorporation of Signature-based Neural Network models, which have recently shown success in temporal tasks. We apply and extend published research providing a full suite of signature-based models. Their components can be used as PyTorch building blocks in future architectures. Sig-Networks enables task-agnostic dataset plug-in, seamless preprocessing for sequential data, parameter flexibility, automated tuning across a range of models. We examine signature networks under three different NLP tasks of varying temporal granularity: counselling conversations, rumour stance switch and mood changes in social media threads, showing SOTA performance in all three, and provide guidance for future tasks. We release the Toolkit as a PyTorch package with an introductory video, Git repositories for preprocessing and modelling including sample notebooks on the modeled NLP tasks.
Anthology ID:
2024.eacl-demo.24
Volume:
Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations
Month:
March
Year:
2024
Address:
St. Julians, Malta
Editors:
Nikolaos Aletras, Orphee De Clercq
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
223–237
Language:
URL:
https://aclanthology.org/2024.eacl-demo.24
DOI:
Bibkey:
Cite (ACL):
Talia Tseriotou, Ryan Chan, Adam Tsakalidis, Iman Munire Bilal, Elena Kochkina, Terry Lyons, and Maria Liakata. 2024. Sig-Networks Toolkit: Signature Networks for Longitudinal Language Modelling. In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations, pages 223–237, St. Julians, Malta. Association for Computational Linguistics.
Cite (Informal):
Sig-Networks Toolkit: Signature Networks for Longitudinal Language Modelling (Tseriotou et al., EACL 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-1/2024.eacl-demo.24.pdf
PDF Search