CLDec 6, 2023

Sig-Networks Toolkit: Signature Networks for Longitudinal Language Modelling

arXiv:2312.03523v2105 citationsh-index: 14Has CodeEACL
Originality Incremental advance
AI Analysis

This provides a practical toolkit for researchers and practitioners working with temporal language data, though it is incremental as it builds on existing signature-based methods.

The authors introduced Sig-Networks, an open-source toolkit for longitudinal language modeling that incorporates signature-based neural network models, achieving state-of-the-art performance on three NLP tasks including counseling conversations, rumour stance switch, and mood changes in social media threads.

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.

Code Implementations2 repos
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes