Abstract: Architecture that generates signals/features that capture the match between intent of a query and category of documents. For example, for a query intent related to “autos”, documents that belong to categories related to “Autos” receive a higher score than documents of a “computers” category. The architecture can be applied to a search ecosystem where query intent classification and document category classifier are available, learns the mapping between query intent and document category, and introduces category-match features to a ranking algorithm, thereby improving search result relevance. The architecture learns the mapping between two existing and different taxonomies to create a category match signal from which the ranking algorithm can learn. Moreover, architecture adapts to a complex ecosystem where different taxonomies on the query side and document side exist through learning a mapping score between at least two taxonomies.

Abstract: Techniques provide time-aware ranking, such as ranking of information, files or URL (uniform resource locator) links. For example, time-aware modeling assists in determining user intent of a query to a search engine. In response to the query, results are ranked in a time-aware manner to better match the user intent. The ranking may model query, URL and query-URL pair behavior over time to create time-aware query, URL and query-URL pair models, respectively. Such models may predict behavior of a query-URL pair, such as frequency and timing of clicks to the URL of the pair when the query of the pair is posed to the search engine. Results of a query may be ranked by predicted query-URL behavior. Once ranked, the results may be sent to the user in response to the query.

Abstract: Methods and systems for multi-tiered information retrieval training are disclosed. A method includes identifying results in a ranked ordering of results that can be swapped without changing a score determined using a first ranking quality measure, determining a first vector and at least one other vector for each identified swappable result in the ranked ordering of results based on the first ranking quality measure and at least one other ranking quality measure respectively, and adding the first vector and the at least one other vector for each identified swappable result in the ranked ordering of results to obtain a function of the first vector and the at least one other vector. Access is provided to the function of the first vector and the at least one other vector for use in the multi-tiered information retrieval training.

Abstract: Described is a technology by which a term frequency function for web click data is machine learned from raw click features extracted from a query log or the like and training data. Also described is using combining the term frequency function with other functions/click features to learn a relevance function for use in ranking document relevance to a query.

Abstract: Described is a technology for identifying sample data items (e.g., documents corresponding to query-URL pairs) having the greatest likelihood of being mislabeled when previously judged, and selecting those data items for re-judging. In one aspect, lambda gradient scores (information associated with ranked sample data items that indicates a relative direction and how “strongly” to move each data item for lowering a ranking cost) are summed for pairs of sample data items to compute re-judgment scores for each of those sample data items. The re-judgment scores indicate a relative likelihood of mislabeling. Once the selected sample data items are re-judged, a new training set is available, whereby a new ranker may be trained.