Ask the GRU: Multi-Task Learning for Deep Text Recommendations

TL;DR

This paper introduces a deep learning approach using GRUs for text-based recommendations, improving accuracy especially in cold-start scenarios by leveraging multi-task learning and sequence information.

Contribution

It presents a novel end-to-end neural network model with GRUs for text encoding in recommendation systems, outperforming prior methods that ignore word order.

Findings

Significantly higher accuracy in scientific paper recommendation.

Outperforms state-of-the-art in cold-start scenarios.

Multi-task learning improves model regularization and performance.

Abstract

In a variety of application domains the content to be recommended to users is associated with text. This includes research papers, movies with associated plot summaries, news articles, blog posts, etc. Recommendation approaches based on latent factor models can be extended naturally to leverage text by employing an explicit mapping from text to factors. This enables recommendations for new, unseen content, and may generalize better, since the factors for all items are produced by a compactly-parametrized model. Previous work has used topic models or averages of word embeddings for this mapping. In this paper we present a method leveraging deep recurrent neural networks to encode the text sequence into a latent vector, specifically gated recurrent units (GRUs) trained end-to-end on the collaborative filtering task. For the task of scientific paper recommendation, this yields models with significantly higher accuracy. In cold-start scenarios, we beat the previous state-of-the-art, all of which ignore word order. Performance is further improved by multi-task learning, where the text encoder network is trained for a combination of content recommendation and item metadata prediction. This regularizes the collaborative filtering model, ameliorating the problem of sparsity of the observed rating matrix.