Xerox Corporation

Microsoft Technology Licensing, LLC

Yahoo! Inc.

Jan O Pedersen

John W Tukey

John Grant Bennett

Trishul A Chilimbi

Michael Joseph Hopcroft

Chad P Walters

Karthik Kalyanaraman

Knut Magne Risvik

Vishesh Parikh

Douglass R Cutting

Hinrich H Schuetze

Chad Carson

David Cho-Lun Ku

Francine R Chen

Daniel Carl Brotsky

Julian M Kupiec

Per-Kristian G Halvorsen

Geoffrey D Nunberg

Steven B Putz

David R Karger

Brett L Kessler

Daniel Gureasko Bobrow

Eric Allan Bier

Dan S Bloomberg

David L Hecht

Ronald M Kaplan

Qi Lu

Henry W Sang, Jr

Gregory T Grefenstette

Pavel Berkhin

Tapas Kanungo

Ashvin Kannan

Martin Kay

D Austin Henderson, Jr

Z Erol Smith, Iii

Rukmini Iyer

Erick Cantu-Paz

Pero Subasic

Hadar Shemtov

Tamas Sarlos

Lauri J Karttunen

Christopher C LuVogt

Mao Yang

Christopher John Leggetter

Frank Zdybel, Jr

Jing Bai

Yue-Sheng Liu

Zoltan Istvan Gyongyi

A new architecture is provided to support a precise information retrieval system on a web scale. The architecture provides algorithms to generate candidates and select the top N results via ranking models (e.g., Semantic ranking models, Aggregation ranking models) to capture term relationships between query and result contents at search-time.

Relevant passage retrieval system

Methods and computer storage media are provided for generating entries for documents in a forward index. A document and its document identification are received, in addition to static features that are query-independent. The document is parsed into tokens to form a token stream corresponding to the document. Relevant data used to calculate rankings of document is identified and a position of the data is determined. The entry is then generated from the document identification, the token stream of the document, the static features, and the positional information of the relevant data. The entry is stored in the forward index.

Efficient forward ranking in a search engine

Methods and systems are provided for using a hybrid-distribution system to identify relevant documents based on a search query. A group of documents is assigned to a particular segment. The group of documents is indexed both by atom and by document to form a reverse index and a forward index. Both indexes are divided amongst each node in that segment so that each node is responsible for storing and accessing a different portion of both the reverse and forward indexes. The reverse index portion is accessed on each of a first set of nodes to identify a first set of documents that is relevant to a particular search query. Document identifications associated with the first set of documents are used to identify a second set of nodes that access their forward index portions to limit the number of relevant documents to a second set of documents.

Hybrid-distribution model for search engine indexes

The subject matter disclosed herein relates to generating an abstract of an electronic document based at least in part on a utility metric associated with a group phrases as well as on a ranked order of sentences.

Generation of search result abstracts

Search results are identified and returned in response to search queries by evaluating and pruning candidate documents in multiple stages. The process employs a search index that indexes atoms found in documents and pre-computed scores for document/atom pairs. When a search query is received, atoms are identified from the search query and a reformulated query is generated based on the identified atoms. The reformulated query is used to identify matching documents, and a preliminary score is generated for matching documents using a simplified scoring function and pre-computed scores in the search index. Documents are pruned based on preliminary scores, and the remaining documents are evaluated using a final ranking algorithm that provides a final set of ranked documents, which is used to generate search results to return in response to the search query.

Matching funnel for large document index

The present invention is directed towards systems and methods for determining the performance of a plurality of versions of a given advertisement. The method of the present invention comprises retrieving a first version of an advertisement and associated click through data, and retrieving a second version of the advertisement and associated click through data. A clickability score is calculated for the first version of the advertisement using the click through data associated with the first version, and a clickability score is calculated for the second version of the advertisement using the click through data associated with the second version. A difference in clickability scores is determined between the first and second advertisement. The clickability score associated with the first version of the advertisement is modified based upon the difference in clickability scores.

System and method for discounting of historical click through data for multiple versions of an advertisement

The present invention is directed towards systems and methods for ranking one or more advertisements. The method of the present invention comprises retrieving a result set comprising one or more advertisements responsive to a request. A clickability score is calculated for the one or more advertisements comprising the result set. An expected revenue value is calculated for the one or more advertisements using the clickability scores of the one or more advertisements as well as an indication of revenue associated with the one or more advertisements. The one or more advertisements are ordered according to the expected revenue of the one or more advertisements.

System and method for revenue based advertisement placement

Techniques for automatically focusing searches conducted by a search engine are provided. According to one aspect, revised query terms are automatically generated based on text in links that are in incoming (and/or outgoing) link lists associated with documents that are referenced in initial search results generated based on initial query terms. For example, some of the phrases that appear in incoming (and/or outgoing) links associated with a result document may be selected. The selected phrases may be added to the initial query terms to generate revised query terms. These revised query terms may be submitted automatically to the search engine in order to produce a more focused list of revised search results. This process may be performed repeatedly, each iteration revising query terms generated by the previous iteration, until specified criteria are satisfied, at which point the final revised search results may be presented to a user.

Determining related terms based on link annotations of documents belonging to search result sets

The present invention is directed towards systems and methods for predicting a frequency with which an advertisement displayed in response to a query will be selected. The method of the present invention comprises receiving analytics data associated with a display of one or more advertisements in response to one or more queries. One or more features associated with the one or more advertisements displayed in response to the one or more queries are identified. One or more functions are generated for predicting a frequency with which a given advertisement displayed in response to a query will be selected using the analytics data and features associated with the one or more advertisements displayed in response to the one or more queries.

System and method for generating functions to predict the clickability of advertisements

A computer implemented method of ranking search hits in a search result set. The computer-implemented method includes receiving a query from a user and generating a list of hits related to the query, where each of the hits has a relevance to the query, where the hits have one or more boosting linked documents pointing to the hits, and where the boosting linked documents affect the relevance of the hits to the query. The method associates a metric to each of at least a subset of the hits, the metric being representative of the number of boosting linked documents that point to each of at least a subset of the hits and which artificially inflate the relevance of the hits. The method then compares the metric, which is representative of the size of a spam farm pointing to the hit, with a threshold value, processes the list of hits to form a modified list based in part on the comparison, and transmits the modified list to the user.

Link-based spam detection

A processor implemented method of identifying the text genre of a machine-readable, untagged text. The processor implemented method begins by generating a cue vector from the text, which represents occurrences in the text of a first set of nonstructural, surface cues, which are easily computable. Afterward, the processor determines whether the text is an instance of a first text genre using the cue vector and a weighting vector associated with the first text genre.

Article and method of automatically determining text genre using surface features of untagged texts

A system, computer readable medium and method for searching for recently altered documents on the World Wide Web is provided. The method selects a server to be searched or crawled by a Web crawler based on a user selected ranking. Servers are ranked by a filter program which compares a user query with the content of a server and the frequency in which content is altered. A top percentage of ranked servers are crawled and the recently altered information, such as hyperlinks, are then provided to the user.

USER QUERY GENERATE SEARCH RESULTS THAT RANK SET OF SERVERS WHERE RANKING IS BASED ON COMPARING CONTENT ON EACH SERVER WITH USER QUERY, FREQUENCY AT WHICH CONTENT ON EACH SERVER IS ALTERED USING WEB CRAWLER IN A SEARCH ENGINE

A method of filtering according to text genre the results of a topic search of a heterogeneous corpus of untagged, machine-readable texts. Because each text of the corpus has a topic and a text genre, the corpus includes multiple text genres and covers multiple topics. According to the method, a processor first searches the corpus for a first multiplicity of texts that have a first topic. Next, the processor identifies a first set of texts of the first multiplicity that are instances of a first text genre and identifies a second set of texts of the first multiplicity that are instances of a second text genre. Finally, the processor identifies to a computer user the first multiplicity of texts in an order based upon the first text genre and second text genre.

Article and method of automatically filtering information retrieval results using test genre

Growing community of inventors

Palo Alto, CA, United States of America

Jan O Pedersen