Authors: Talia Tseriotou, Ryan Sze-Yin Chan, Adam Tsakalidis, Iman Munire Bilal, Elena Kochkina, Terry Lyons, Maria Liakata

Published on: December 06, 2023

Impact Score: 8.22

Arxiv code: Arxiv:2312.03523

Summary

• What is new: First toolkit for longitudinal language modelling using Signature-based Neural Network models.
• Why this is important: Lack of specialized toolkits for temporal tasks in language modelling.
• What the research proposes: Sig-Networks toolkit that incorporates signature-based models for longitudinal language modelling.
• Results: State-of-the-art performance in counselling conversations, rumour stance switch, and mood changes in social media threads.

Technical Details

Technological frameworks used: PyTorch

Models used: Signature-based Neural Network models

Data used: Counselling conversations, Rumour stance switch, Mood changes in social media threads

Potential Impact

AI research, NLP applications, Social media platforms, Mental health platforms, Rumour analysis tools

Want to implement this idea in a business?

We have generated a startup concept here: TemporalText AI.