Neural Endorsement Based Contextual Suggestion

This paper presents the University of Amsterdam's participation in the TREC 2016 Contextual Suggestion Track. In this research, we have studied a personallized neural document language modeling and a neural category preference modeling for contextual suggestion using available endorsementsin TREC 2016 contextual suggestion track phase 2 requests. Specically, our main aim is to answer the questions: How to model users' proles by using the suggestions' endorsements as an additional data? How eective is using word embeddings to boost terms' weights relevant to the given endorsements? How to model users' attractioncategory preferences? How eective is using deep neural networks to learn users' category preferences in contextual suggestion task? Our main ndings are the following: First,
the neural personalized document based user proling using word embeddings improves the baseline content-based ltering approach based on all the common IR measures including TREC 2016 Contextual Suggestion ocial metric (NDCG@5).
Second, neural users' category preference modeling beats both baseline content-based ltering and the user proling model using word-embeddings in terms of all the
common IR measures.