Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.