Academisch-cultureel centrum SPUI25, Spui, Amsterdam, Netherlands

SEA: Search Engines Amsterdam – Monthly Friday Seminar

This Friday, we’ll have two talks followed by drinks.

Christophe Van Gysel from ILPS-UVA will give the academic talk. The industry talk will be given by Philips.

This edition of SEA will be held in SPUI25.


16:00 – 16:30 Christophe van Gysel

16:30 – 17:00 Philips

17:00 – 18:00 Drinks & Snacks

Details of the talks:

Christophe van Gysel — Learning Latent Vector Spaces for Product Search

We introduce a novel latent vector space model that jointly learns the latent representations of words, e-commerce products and a mapping between the two without the need for explicit annotations. The power of the model lies in its ability to directly model the discriminative relation between products and a particular word. We compare our method to existing latent vector space models (LSI, LDA and word2vec) and evaluate it as a feature in a learning to rank setting. Our latent vector space model achieves its enhanced performance as it learns better product representations. Furthermore, the mapping from words to products and the representations of words benefit directly from the errors propagated back from the product representations during parameter estimation. We provide an in-depth analysis of the performance of our model and analyze the structure of the learned representations.



Brands need to leverage the enormous volumes of feedback that consumers leave on social media. Existing methods for understanding free-text based consumer feedback data (eg online reviews) are predominantly qualitative (eg sentiment analysis). Qualitative approaches, however, cannot provide quantitative predictions of a potential rating increase following a product improvement. This paper will describe a novel method that converts reviews and ratings into statistical data that can be used to forecast rating performance. This is achieved by assigning quantitative values of importance to the various features of a given product based on each feature’s percentage contribution to the product rating. With such information, marketing and innovation teams can optimise their investment decisions to address consumer needs accurately and therefore maximise return on investment.