Distributed-Representation Based Hybrid Recommender System with Short Item Descriptions

no code implementations • 15 Mar 2017 • Junhua He, Hankz Hankui Zhuo, Jarvan Law

We find that there are often "short" texts describing features of items, based on which we can approximate the similarity of items and make recommendation together with rating scores.

Collaborative Filtering Recommendation Systems

LTSG: Latent Topical Skip-Gram for Mutually Learning Topic Model and Vector Representations

no code implementations • 23 Feb 2017 • Jarvan Law, Hankz Hankui Zhuo, Junhua He, Erhu Rong

Some other models use the information trained from external large corpus to help improving smaller corpus.

Topic Models Word Embeddings