Learning to refine text based recommendations

摘要

We propose a text-based recommendation engine that utilizes recurrent neural networks to flexibly map textual input into continuous vector representations tailored to the recommendation task. Here, the text objects are documents such as Wikipedia articles or question and answer pairs. As neural models require substantial training time, we introduce a sequential component so as to quickly adjust the learned metric over objects as additional evidence accrues. We evaluate the approach on recommending Wikipedia descriptions of ingredients to their associated product categories. We also exemplify the sequential metric adjustment on retrieving similar Stack Exchange AskUbuntu questions. 1