Google Inc.

Sarveshwar Duddu

Kartik Singh

Lev Finkelstein

Thorsten Brants

Minh Tue Vo Thanh

Kuntal Loya

Franz Josef Och

Vance Julius Vagell

Joshua James Estelle

Sarah Cooper

Shankar Kumar

Eahab Ibrahim

Avishek Banerjee

A server is configured to receive, from a client, a query and context information associated with a document; obtain search results, based on the query, that identify documents relevant to the query; analyze the context information to identify content; generate first scores for a hierarchy of topics, that correspond to measures of relevance of the topics to the content; select a topic that is most relevant to the context information when the topic is associated with a greatest first score; generate second scores for the search results that correspond to measures of relevance, of the search results, to the topic; select one or more of the search results as being most relevant to the topic when the search results are associated with one or more greatest second scores; generate a search result document that includes the selected search results; and send, to a client, the search result document.

Context-based filtering of search results

A method for fact correction and completion during document drafting. The method includes receiving a first user input comprising text being added to an electronic document and initiating a fact correction mode. The fact correction mode includes parsing the text to identify a factual proposition and determining the accuracy of the factual proposition. If the factual proposition is inaccurate, the mode includes displaying a visual indication of the inaccuracy of the factual proposition; receiving a second user input comprising an indication selecting the inaccurate factual proposition; displaying a menu that includes a correction element wherein the correction element is based on an accurate factual proposition related to the inaccurate factual proposition; receiving a third user input comprising an indication selecting the correction element; and modifying the electronic document by replacing at least a portion of the inaccurate factual proposition with at least a portion of the accurate factual proposition.

Fact correction and completion during document drafting

Methods, systems and apparatus are described herein that include receiving a partial query entered into a search field on a computing device, and data indicating a document presented on the computing device during entry of the partial query. Search results are then obtained which identify respective lists of search results documents for corresponding candidate query completions in a set obtained for the partial query. Similarity scores are then calculated for candidate query completions based at least in part on a similarity between content in the displayed document and content in search result documents in the corresponding lists. One or more candidate query completions in the set are then selected as refined query completions for the partial query based at least in part on the similarity scores and provided for presentation by the computing device.

Query completions in the context of a presented document

Methods, and systems, including computer programs encoded on computer-readable storage mediums, including a method for identifying quotations occurring in resources. The method includes identifying first and second quotations that occur in particular resources in a set of resources, each particular resource being classified as a quotation-related resource; determining, for each of the first and second quotations, a number of occurrences of the quotation in the set and a number of different resources in the set in which the quotation occurs; determining that the first quotation and the second quotation are (i) semantically related and (ii) not identical; selecting a representative quotation from among the first quotation and the second quotation; and storing the representative quotation, the number of occurrences of the representative quotation and the number of different resources in which the representative quotation occurs in association with an entity to which the representative quotation is attributed.

Quotation identification

Methods, systems and apparatus are described herein that include receiving a partial query entered into a search field on a computing device, and data indicating a document presented on the computing device during entry of the partial query. The presented document has been edited by a user of the computing device. Search results are then obtained which identify respective lists of search results documents for corresponding candidate query completions in a set obtained for the partial query. Similarity scores are then calculated for candidate query completions based at least in part on a similarity between content in the displayed document and content in search result documents in the corresponding lists. One or more candidate query completions in the set are then selected as refined query completions for the partial query based at least in part on the similarity scores and provided for presentation by the computing device.

Query completions in the context of a user's own document

A system and method for suggesting a recipient of content. An interest profile of at least one contact of a user is determined based on at least one endorsement action of the at least one contact directed to a type of content. A type of content of an unpublished post of the user is determined. The at least one contact is identified as a suggested recipient of the unpublished post of the user based on the interest profile of the at least one contact and the type of content of the unpublished post of the user. The suggested recipient of the unpublished post of the user is provided for display.

Suggesting a recipient of content

A computer-implemented method includes receiving a document and a request to translate the document to a different language, the document including at least one tag associated with a first portion of text within the document, receiving a manual translation of the document translated by a human translator but not including the at least one tag, generating a plurality of alignments between the document and the manual translation using a statistical alignment model, selecting one of the plurality of alignments based on a likelihood that the first portion of text in the document corresponds to an aligned second portion of text within the manual translation, mapping a location of the tag in the document to a corresponding location within the manual translation based on the selected alignment, and inserting the at least one tag into the manual translation at the corresponding location to obtain a modified manual translation of the document.

Growing community of inventors

Bengaluru, India

Sarveshwar Duddu