Microsoft Technology Licensing, LLC

Shuming Shi

Ji-Rong Wen

Wei-Ying Ma

Zhiwei Li

Zaiqing Nie

Qing Yu

Ming Li

Fei Xing

Mingjie Zhu

Yunbo Cao

Ruihua Song

Chin-Yew Lin

Nan Sun

Yunxiao Ma

Guomao Xin

This disclosure describes, in part, techniques for operating a search query user interface to allow seamless creating, editing and/or refining of a search query using various interactive functions. The techniques described herein may display a search query divided into segments. A selection of a segment of the search query may then be received. One or more alternatives to the selected segment may then be presented. Next, a selection of one of the presented alternative may be received. As a result, the search query may be altered using the selected alternative. Furthermore, the techniques described herein allow a user to operate on a search query using query substitution, expansion, association and/or history functions.

Search query user interface

A topic modeling architecture is used to discover high-quality semantic classes from a large collection of raw semantic classes (RASCs) for use in generating responses to queries. A specific semantic class is identified from a collection of RASCs, and a preprocessing operation is conducted to remove one or more items with a semantic class frequency less than a predetermined threshold. A topic model is then applied to the specific semantic class for each of the items that remain in the specific semantic class after the preprocessing operation. A postprocessing operation is then conducted on the items of the specific semantic class to merge and sort the results of the topic model and generate final semantic classes for use by a search engine to respond to a query.

Employing topic models for semantic class mining

A method and system for determining relevance of a document having text and images to a text string is provided. A scoring system identifies image text associated with an image of the document. The scoring system calculates an image score indicating relevance of the image text to the text string. The image score may be used in many applications, such as searching, summary generation, and document classification, image search, and image classification.

Scoring relevance of a document based on image text

A method and system for determining dominance of the media elements of display pages is provided. The dominance system provides a scoring mechanism for scoring the dominance of media elements of display pages based on features of each media element of the display page. To generate the scores for the media elements of the display page, the dominance system first identifies the media elements and then identifies the features of the media elements. The dominance system then scores the identified media elements using the provided scoring mechanism and the identified features.

Adding dominant media elements to search results

A learning system for a search ranking function model may include a computer program that iteratively refines the model using new queries and associated documents from an unlabeled training set. The unlabeled training set may include a set of queries for which the associated documents have not been labeled as 'relevant' or otherwise labeled. The new queries may be selected based on a similarity to and an accuracy of each neighbor from a labeled training set, such as a labeled validation set. Upon selection, the documents associated with the new queries may be labeled. The new queries and their associated documents may be accumulated into a labeled training set, such as a labeled training set, and a refined model may be learned based on the augmented labeled training set. The model may be iteratively refined until it is determined that the model is adequate.

Query selection for effectively learning ranking functions

A search method uses pseudo-anchor text associated with search objects to improve search performance. The pseudo-anchor text may be extracted in combination with an identifier of the search objects (such as a pseudo-URL) from a digital corpus such as a collection of documents. Pseudo-anchor texts for each object are preferably extracted from candidate anchor blocks using a machine learning based approach. The pseudo-anchor texts are made available for searching and used to help rank the objects in a search result to improve search performance. The method may be used in vertical search of objects such as published articles, products and images that lack explicit URLs and anchor text information.

Pseudo-anchor text extraction

A method and system is provided for determining relevance of an object to a term based on a language model. The relevance system provides records extracted from web pages that relate to the object. To determine the relevance of the object to a term, the relevance system first determines, for each record of the object, a probability of generating that term using a language model of the record of that object. The relevance system then calculates the relevance of the object to the term by combining the probabilities. The relevance system may also weight the probabilities based on the accuracy or reliability of the extracted information for each data source.

Web object retrieval based on a language model

A search method uses pseudo-anchor text associated with search objects to improve search performance. The pseudo-anchor text may be extracted in combination with an identifier of the search objects (such as a pseudo-URL) from a digital corpus such as a collection of documents. Pseudo-anchor texts for each object are preferably extracted from candidate anchor blocks using a machine learning based approach. The pseudo-anchor texts are made available for searching and used to help ranking the objects in a search result to improve search performance. Method may be used in vertical search of objects such as published articles, products and images that lack explicit URL and anchor text information.

Pseudo-anchor text extraction for vertical search

A method and system for determining relevance of a document to a query based on identifier match distance is provided. The relevance system analyzes a training set of queries and documents to determine the relationship between identifier match distance and relevance of a document to a query. The identifier match distance indicates the distance from the end of an identifier of a document to an identifier term that matches a query term. The relevance system generates a prior relevance probability that a document with a certain identifier match distance is relevant to a query. The relevance system uses the prior relevance probabilities to determine relevance of documents to queries based on identifier match distance.

Growing community of inventors

Beijing, China

Shuming Shi