Microsoft Technology Licensing, LLC

Yahoo! Inc.

Sony Corporation

Sony Electronics Inc

Lei Duan

Xavier Menendez-Pidal

Lex S Olorenshaw

Fan Li

Deepayan Chakrabarti

Srinivas Vadrevu

Seokkyung Chung

Swapnil Hajela

Emre Velipasaoglu

Jingwen Lu

Benoit F Dumoulin

Omar Rogelio Alonso

Kostas Tsioutsiouliklis

Michael Ching

Gilbert Leung

Charles C Carson, Jr

Rajesh Shenoy

Dmitri Pavlovski

Yumao Lu

Gustavo Hernandez Abrego

Su Chan

Satish Kumar Musukula

Xing Wei

Paul Alexander Dow

Lei Guo

Yajie Siamwalla

Guenther Schmuelling

Wenbo Wang

Will Chin

Hemant Purohit

Ki Yeun Kim

Architecture that automatically generate concise descriptions of users in social media. The descriptions communicate classification or category of a given social media user in a small amount of viewing space. The description can be based on available metadata (e.g., user profile biography) and/or other information about that person, as may be obtained from the information data sources (e.g., structured knowledge bases) on networks such as the Internet and enterprises, for example. The descriptions can also be query-dependent, by assuming there is some relationship between the social media user and a query, in which case, the descriptions illustrate that relationship.

Derivation and presentation of expertise summaries and interests for users

One or more techniques and/or systems are provided for indexing content based upon index features (e.g., temporal features, user engagement features, and/or outlier features), and/or for providing content within a search result interface based upon such index features and/or rankings. For example, user reaction data associated with content (e.g., a microblog message, a social network post, etc.) may be evaluated to generate a user engagement feature that may be constrained to a time window feature (e.g., the number of shares of a message within the first 10 minutes from publication of the message) to create an index feature for indexing the content within a content index. Responsive to the index feature corresponding to a search query, the content may be provided with search results for the search query. For example, the content may correspond to trending or breaking news associated with the search query.

Temporal user engagement features

Exemplary methods and apparatuses are provided which may be used for classifying and indexing segmented portions of web pages and providing related information for use in information extraction and/or information retrieval systems. In an embodiment, an index of segmented portions may be used by a search engine to respond to a search query. In an embodiment, one or more machine learned models may be used to identify one or more feature properties of a plurality of segmented portions within one or more files, or otherwise inferable from the one or more files. In an embodiment, one or more machine learned models may be used to classify one or more of a plurality of segmented portions as being at least one of a plurality of segment types.

Automatic classification of segmented portions of web pages

Systems, methods, and computer-readable storage media for presenting supplemental search results having indications that identified documents have been endorsed by the user and/or social network connections of the user are provided. A search query is received and it is determined that the user's social networking data is available. Documents that have been endorsed by the user and/or social network connections of the user are searched to identify those that satisfy the input search query. The satisfying documents are assigned a relevance score to determine whether each satisfying document is relevant enough to be shown and to determine placement of the document on the SERP relative to standard search results. Upon rendering of the SERP, a supplemental search result identifying documents that were endorsed by the user and/or social network connections of the user is presented, as is an indication about which social network connection(s) of the user endorsed the document.

Supplemental search results having social connection endorsement data on a SERP

A plurality of web documents that include indicators corresponding to one or more selectable like objects may be obtained. A corresponding web domain associated with each of the plurality of obtained web documents may be determined. A domain total like object count of the indicators corresponding to the one or more selectable like objects may be determined for each one of the obtained plurality of web documents, for each determined corresponding web domain. A candidate group of the corresponding web domains may be determined based on a comparison of a predetermined first threshold value with one or more of the domain total like object counts. A likefarm domain confidence score may be determined for each one of a second group of the corresponding web domains based on a decision tree function that is based on a plurality of domain attributes.

Likefarm determination

Exemplary methods and apparatuses are provided which may be used for classifying and indexing segmented portions of web pages and providing related information for use in information extraction and/or information retrieval systems.

Unsupervised clustering can be used for organization of micro-blog or other short length messages into message clusters. Messages can be compared with existing clusters to determine a similarity score. If at least one similarity score is greater than a threshold value, a message can be added to an existing message cluster. If a message is not similar to an existing cluster, the message can be compared against criteria for starting a new message cluster.

Unsupervised message clustering

In one embodiment, access a search query comprising one or more query words, at least one of the query words representing one or more query concepts; access a network document identified for a search query by a search engine, the network document comprising one or more document words, at least one of the document words representing one or more document concepts; semantic-text match the search query and the network document to determine one or more negative semantic-text matches; and construct one or more negative features based on the negative semantic-text matches.

Semantic and text matching techniques for network search

A system for detecting artificial promotion of a resource, including a search engine operative to index a set incoming links ('inlinks') which reference the resource, a log module coupled with the search engine and configured to store log data associated with the set of inlinks, a partitioning module coupled with log module and operative to partition the set of inlinks into a plurality of groups of inlinks based on at least one partitioning scheme, a statistics module coupled with the partitioning module and operative to compute a statistic associated with the inlinks within each of the plurality of groups of inlinks, and a computation module coupled with the statistics module and operative to process the computed statistic associated with the inlinks of each of the plurality of groups of inlinks and compute a metric associated with set of inlinks where the metric indicates a level of uniformity of a distribution of values of the respective computed statistics among the plurality of groups of inlinks, and where the search engine places a list of search results, generated in response to a search query, in a pattern based on the metric.

Detection of undesirable web pages

A system and method for effectively implementing an optimized language model for speech recognition includes initial language models each created by combining source models according to selectable interpolation coefficients that define proportional relationships for combining the source models. A rescoring module iteratively utilizes the initial language models to process input development data for calculating word-error rates that each correspond to a different one of the initial language models. An optimized language model is then selected from the initial language models by identifying an optimal word-error rate from among the foregoing word-error rates. The speech recognizer may then utilize the optimized language model for effectively performing various speech recognition procedures.

System and method for effectively implementing an optimized language model for speech recognition

The present invention comprises a system and method for implementing a Mandarin Chinese speech recognizer with an optimized phone set, and may include a recognizer configured to compare input speech data to phone strings from a vocabulary dictionary that is implemented according to an optimized Mandarin Chinese phone set. The optimized Mandarin Chinese phone set may be implemented with a phonetic technique to separately include consonantal phones and vocalic phones. For reasons of system efficiency, the optimized Mandarin Chinese phone set may preferably be implemented in a compact manner to include only a minimum required number of consonantal phones and vocalic phones to accurately represent Mandarin Chinese speech during the speech recognition procedure.

System and method for Mandarin Chinese speech recognition using an optimized phone set

The present invention comprises a system and method for effectively implementing a Mandarin Chinese speech recognition dictionary, and may include a recognizer configured to compare input speech data to phone strings from a vocabulary dictionary that is implemented according to an optimized Mandarin Chinese phone set. The optimized Mandarin Chinese phone set may efficiently be implemented by utilizing an allophone and phonemic variation technique. In addition, the foregoing vocabulary dictionary may be implemented by utilizing unified dictionary optimization techniques to provide robust and accurate speech recognition. Furthermore, the vocabulary dictionary may be implemented as an optimized dictionary to accurately recognize either Northern Mandarin Chinese speech or Southern Mandarin Chinese speech during the speech recognition procedure.

Growing community of inventors

San Jose, CA, United States of America

Lei Duan