Fernando Díaz

Learning to Match Using Local and Distributed Representations of Text\n for Web Search

2016 · arXiv (Cornell University)

Models such as latent semantic analysis and those based on neural embeddings\nlearn distributed representations of text, and match the query against the\ndocument in the latent semantic space. In traditional information retrieval\nmodels, on the other hand, …

Query Expansion with Locally-Trained Word Embeddings

2016

Continuous space word embeddings have received a great deal of attention in the natural language processing and machine learning communities for their ability to model term similarity and other relationships. We study the use of …

Learning to Match using Local and Distributed Representations of Text for Web Search

2017

Models such as latent semantic analysis and those based on neural embeddings learn distributed representations of text, and match the query against the document in the latent semantic space. In traditional information retrieval models, on …

Evaluating Stochastic Rankings with Expected Exposure

2020

We introduce the concept of expected exposure as the average attention ranked items receive from users over repeated samples of the same query. Furthermore, we advocate for the adoption of the principle of equal expected …