Open Domain Suggestion Mining Leveraging Fine-Grained Analysis

TL;DR

This paper introduces a novel two-tier pipeline combining discourse marker oversampling and fine-grained analysis to improve open domain suggestion mining from online forums, outperforming existing methods.

Contribution

It presents a new pipeline that effectively handles semantic complexity and domain diversity in suggestion mining, leveraging oversampling and transformer-based analysis.

Findings

Outperforms state-of-the-art suggestion mining methods

Effective in diverse real-world online forum datasets

Provides insights into deployment and reproducibility

Abstract

Suggestion mining tasks are often semantically complex and lack sophisticated methodologies that can be applied to real-world data. The presence of suggestions across a large diversity of domains and the absence of large labelled and balanced datasets render this task particularly challenging to deal with. In an attempt to overcome these challenges, we propose a two-tier pipeline that leverages Discourse Marker based oversampling and fine-grained suggestion mining techniques to retrieve suggestions from online forums. Through extensive comparison on a real-world open-domain suggestion dataset, we demonstrate how the oversampling technique combined with transformer based fine-grained analysis can beat the state of the art. Additionally, we perform extensive qualitative and qualitative analysis to give construct validity to our proposed pipeline. Finally, we discuss the practical, computational and reproducibility aspects of the deployment of our pipeline across the web.