Saved in:
Bibliographic Details
Main Authors: Tseriotou, Talia, Chan, Ryan Sze-Yin, Tsakalidis, Adam, Bilal, Iman Munire, Kochkina, Elena, Lyons, Terry, Liakata, Maria
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2312.03523
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909094689898496
author Tseriotou, Talia
Chan, Ryan Sze-Yin
Tsakalidis, Adam
Bilal, Iman Munire
Kochkina, Elena
Lyons, Terry
Liakata, Maria
author_facet Tseriotou, Talia
Chan, Ryan Sze-Yin
Tsakalidis, Adam
Bilal, Iman Munire
Kochkina, Elena
Lyons, Terry
Liakata, Maria
contents 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 pre-processing 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.
format Preprint
id arxiv_https___arxiv_org_abs_2312_03523
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Sig-Networks Toolkit: Signature Networks for Longitudinal Language Modelling
Tseriotou, Talia
Chan, Ryan Sze-Yin
Tsakalidis, Adam
Bilal, Iman Munire
Kochkina, Elena
Lyons, Terry
Liakata, Maria
Computation and Language
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 pre-processing 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.
title Sig-Networks Toolkit: Signature Networks for Longitudinal Language Modelling
topic Computation and Language
url https://arxiv.org/abs/2312.03523