University of Washington

Netbot, Inc.

Other

Microsoft Technology Licensing, LLC

Farecast, Inc.

Oren Etzioni

Craig A Knoblock

Alexander Yates

Rattapoom Tuchinda

Kobi Isaac Reiter

Michele Banko

Daniel S Weld

Robert B Doorenbos

Chung Kwok

Gregory Lauckhart

Erik Selberg

Michael J Cafarella

David Christianson

Marcus Sammer

Michael Schmitz

Stephen Soderland

Hugh Crean

Jay Bartot

Michael Fridgen

Atsushi Sugiura

David Hsu

To implement open information extraction, a new extraction paradigm has been developed in which a system makes a single data-driven pass over a corpus of text, extracting a large set of relational tuples without requiring any human input. Using training data, a Self-Supervised Learner employs a parser and heuristics to determine criteria that will be used by an extraction classifier (or other ranking model) for evaluating the trustworthiness of candidate tuples that have been extracted from the corpus of text, by applying heuristics to the corpus of text. The classifier retains tuples with a sufficiently high probability of being trustworthy. A redundancy-based assessor assigns a probability to each retained tuple to indicate a likelihood that the retained tuple is an actual instance of a relationship between a plurality of objects comprising the retained tuple. The retained tuples comprise an extraction graph that can be queried for information.

Open information extraction from the web

Techniques are described for using predictive pricing information for items to assist in evaluating buying and/or selling decisions in various ways, such as on behalf of end-user item acquirers and/or intermediate item providers. The predictive pricing for an item may be based on an analysis of historical pricing information for that item and/or related items, and can be used to make predictions about future pricing information for the item. Such predictions may then be provided to users in various ways to enable comparison of current prices to predicted future prices. In some situations, predictive pricing information is used to assist customers when purchasing airline tickets and/or to assist travel agents when selling airline tickets. This abstract is provided to comply with rules requiring an abstract, and it is submitted with the intention that it will not be used to interpret or limit the scope or meaning of the claims.

Performing predictive pricing based on historical data

A translation graph is created using a plurality of reference sources that include translations between a plurality of different languages. Each entry in a source is used to create a wordsense entry, and each new word in a source is used to create a wordnode entry. A pair of wordnode and wordsense entries corresponds to a translation. In addition, a probability is determined for each wordsense entry and is decreased for each translation entry that includes more than a predefined number of translations into the same language. Bilingual translation entries are removed if subsumed by a multilingual translation entry. Triangulation is employed to identify pairs of common wordsense translations between a first, second, and third language. Translations not found in reference sources can also be inferred from the data comprising the translation graph. The translation graph can then be used for searches of a data collection in different languages.

Use of lexical translations for facilitating searches

Techniques are described for using predictive pricing information for items to assist in evaluating buying and/or selling decisions in various ways, such as on behalf of end-user item acquirers and/or intermediate item providers. The predictive pricing for an item may be based on an analysis of historical pricing information for that item and/or related items, and can be used to make predictions about future pricing information for the item. Such predictions may then be provided to users in various ways to enable comparison of current prices to predicted future prices. In some situations, predictive pricing information is used to assist customers when purchasing airline tickets and/or to assist travel agents when selling airline tickets.

Open information extraction from the Web

A method and system for protecting prices is provided. The price protection system increases consumer confidence when making purchases by reducing the risk associated with fluctuating prices. The price protection system receives a purchase specification from a consumer. Next, the price protection system determines the risk that the prices of items matching the purchase specification will change and reports a protected price to the consumer that represents the price that the price protection system will protect based on the determined risk for a protection period. Finally, the price protection system receives a request from the consumer to purchase protection of the protected price.

System and method of protecting prices

An information search device capable of selecting topic search engines (i.e., search engines that focus on specific topics) that are appropriate to a user's search keywords when searching the Web on the Internet. Terms having relevance to each topic search engine are collected from, for example, the Web, and a DB selection index for selecting search engines is produced in advance by an index generator. When a search keyword is supplied from a user, terms having relevance to the search keyword are acquired from a general-purpose Web search engine by means of a query expansion unit. The thus-acquired terms are matched with terms stored in the DB selection index, and topic search engines having a high incidence of matching are presented to the user.

Information search device and information search method using topic-centric query routing

This invention provides assistance to a user in accessing network attached information sources. In one aspect, the invention is a method for intelligently routing a user query to information sources relevant to that query, extracting relevant data fields from received responses, and intelligently presenting the extracted data in order of estimated relevance. The system of this invention implements one or more steps of the method in a centralized or distributed manner on one or more network attached computers. Further, this invention provides a novel language and implementation that facilitates easily written and maintained descriptions of information source query and response formats.

Method and system using information written in a wrapper description

Growing community of inventors

Seattle, WA, United States of America

Oren Etzioni