Graphite: A Graph-based Extreme Multi-Label Short Text Classifier for Keyphrase Recommendation
This addresses the need for efficient, interpretable keyphrase recommendations for advertisers and sellers in resource-constrained online platforms, though it appears incremental as it builds on existing graph-based and XML methods.
The paper tackles the problem of real-time keyphrase recommendation in advertising and e-commerce by framing it as an extreme multi-label short text classification, and presents Graphite, a graph-based classifier that matches standard models in performance while being lightweight and not requiring GPU resources, enabling training on large datasets where state-of-the-art models fail.
Keyphrase Recommendation has been a pivotal problem in advertising and e-commerce where advertisers/sellers are recommended keyphrases (search queries) to bid on to increase their sales. It is a challenging task due to the plethora of items shown on online platforms and various possible queries that users search while showing varying interest in the displayed items. Moreover, query/keyphrase recommendations need to be made in real-time and in a resource-constrained environment. This problem can be framed as an Extreme Multi-label (XML) Short text classification by tagging the input text with keywords as labels. Traditional neural network models are either infeasible or have slower inference latency due to large label spaces. We present Graphite, a graph-based classifier model that provides real-time keyphrase recommendations that are on par with standard text classification models. Furthermore, it doesn't utilize GPU resources, which can be limited in production environments. Due to its lightweight nature and smaller footprint, it can train on very large datasets, where state-of-the-art XML models fail due to extreme resource requirements. Graphite is deterministic, transparent, and intrinsically more interpretable than neural network-based models. We present a comprehensive analysis of our model's performance across forty categories spanning eBay's English-speaking sites.