End-to-end Learning for Short Text Expansion
This addresses the challenge of sparse information in short texts for applications like search engines and social media, offering a novel method for a known bottleneck.
The paper tackles the problem of short text analysis by proposing an end-to-end learning approach that automatically expands short texts to optimize a given task, using a novel deep memory network to find relevant information from longer documents. It demonstrates significant performance improvements over classical methods in short text classification on real-world datasets.
Effectively making sense of short texts is a critical task for many real world applications such as search engines, social media services, and recommender systems. The task is particularly challenging as a short text contains very sparse information, often too sparse for a machine learning algorithm to pick up useful signals. A common practice for analyzing short text is to first expand it with external information, which is usually harvested from a large collection of longer texts. In literature, short text expansion has been done with all kinds of heuristics. We propose an end-to-end solution that automatically learns how to expand short text to optimize a given learning task. A novel deep memory network is proposed to automatically find relevant information from a collection of longer documents and reformulate the short text through a gating mechanism. Using short text classification as a demonstrating task, we show that the deep memory network significantly outperforms classical text expansion methods with comprehensive experiments on real world data sets.