Machine Learning for Retrieval

This research area applies machine learning techniques to improve various aspects of information retrieval, from ranking and matching to cross-market adaptation and personalization. Key work includes developing neural ranking models that combine local and distributed text representations, creating density-based user representations using Gaussian process regression for multi-interest personalization, and learning to rank with labeled features rather than document labels. The research encompasses cross-market model adaptation using pairwise preference data, methods for transferring retrieval knowledge across collections with non-overlapping vocabularies, and techniques for generating quick links and proactive suggestions.