Michael J Cafarella, Age 5163 Bowdoin St, Newton Highlands, MA 02461

7698446, Apr 13, 2010

Jul 18, 2008

12/176259

Michael Cafarella - San Francisco CA, US
Brandon Porter - Foster City CA, US
Will H. Scullin - San Francisco CA, US

TellMe Networks - Mountain View CA

G06F 15/16

709229, 709227, 709206

A system and method are provided for an intermediate party to facilitate an interactive telephony session between a customer and a sender of a request for the session. The sender can provide the request to the intermediate party via electronic mail. The request includes the information to initiate the interactive telephony session with the customer as well as the information to conduct that session. In one embodiment, the information to conduct the interactive telephony session includes a URL that provides an application in VoiceXML (Voice Extensible Markup Language). The intermediate party can initiate and conduct the session at the appropriate time and provide the sender with a status regarding the session. During the session, the customer can respond with voice or DTMF inputs to various prompts, thereby proceeding with a transaction and/or providing valuable feedback to the sender.

7877343, Jan 25, 2011

Apr 2, 2007

11/695506

Michael J. Cafarella - Seattle WA, US
Michele Banko - Seattle WA, US
Oren Etzioni - Seattle WA, US

University of Washington through its Center for Commercialization - Seattle WA

G06E 1/00
G06F 15/18

706 20, 705 5, 382104

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.

2002009, Jul 25, 2002

Jan 24, 2001

09/769635

Michael Cafarella - San Francisco CA, US
Brandon Porter - Mountain View CA, US
Will Scullin - San Francisco CA, US

G06F015/16

709/206000

A system and method are provided for an intermediate party to facilitate an interactive telephony session between a customer and a sender of a request for the session. The sender can provide the request to the intermediate party via electronic mail. The request includes the information to initiate the interactive telephony session with the customer as well as the information to conduct that session. In one embodiment, the information to conduct the interactive telephony session includes a URL that provides an application in VoiceXML (Voice Extensible Markup Language). The intermediate party can initiate and conduct the session at the appropriate time and provide the sender with a status regarding the session. During the session, the customer can respond with voice or DTMF inputs to various prompts, thereby proceeding with a transaction and/or providing valuable feedback to the sender.

2011019, Aug 4, 2011

Dec 16, 2010

12/970155

Michael J. Cafarella - Seattle WA, US
Michele Banko - Seattle WA, US
Oren Etzioni - Seattle WA, US

University of Washington through its Center for Commercialization - Seattle WA

G06F 15/18
G06F 17/30

706 12, 707769, 707723, 707E17014, 707E17045

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.

2014003, Jan 30, 2014

Jul 26, 2013

13/952468

Michael Cafarella - Ann Arbor MI, US
Michele Banko - Seattle WA, US

G06F 17/27

704 9

A system for identifying relational tuples is provided. The system extracts a relation phrase from a sentence by identifying a verb in the sentence and then identifying a relation phrase of the sentence as a phrase in the sentence starting with the identified verb that satisfies both a syntactic constraint and a lexical constraint. The system also identifies arguments for a relation phrase. To extract the arguments, the system applies a left-argument-left-bound classifier, a left-argument-right-bound classifier, and a right-argument-right-bound classifier to identify a left argument and right argument for the relation phrase such that the left argument, the relation phrase, and the right argument form a relational tuple.

2016009, Apr 7, 2016

Oct 3, 2014

14/494047

- Ann Arbor MI, US
Thomas Friedrich WENISCH - Ann Arbor MI, US
Michael John CAFARELLA - Ann Arbor MI, US

G06F 17/30

A hardware accelerator for performing queries into, for example, an indexed text log files is formed of plurality of hardware execution units (text engines) each executing a partial query program upon the same full set of input data. These partial query programs may switch between different query algorithms on up to a per-character basis. The sequence of data when loaded into a buffer memory for querying may be searched for delimiters as the data is loaded. The hardware execution units may support a number match program instruction which serves to identify a numeric variable, and to determine a value of that numeric variable located at a variable position within a sequence of characters being queried.

2016009, Apr 7, 2016

Sep 23, 2015

14/862350

- Ann Arbor MI, US
Thomas Friedrich WENISCH - Ann Arbor MI, US
Michael John CAFARELLA - Ann Arbor MI, US

G06F 17/30

A hardware accelerator for performing queries into, for example, an indexed text log files is formed of plurality of hardware execution units (text engines) , each executing a partial query program upon the same full set of input data. These partial query programs may switch between different query algorithms on up to a per-character basis. The sequence of data when loaded into a buffer memory for querying may be searched for delimiters as the data is loaded. The hardware execution units may support a number match program instruction which serves to identify a numeric variable, and to determine a value of that numeric variable located at a variable position within a sequence of characters being queried.