AT&T Intellectual Property I, LP

At+t Corp.

Telelogue, Inc.

Rutgers, the State University of New Jersey

Nuance Communications, Inc.

Esther Levin

Roberto Pieraccini

David Crawford Gibbon

Behzad Shahraray

Andrea Basso

Mazin E Gilbert

Mehmet Reha Civanlar

Qian Huang

Ilija Zeljkovic

Robert Elias Schapire

Amir M Mane

Susan Jeanne Boyce

Michael Lederman Littman

Shrikanth Sambasivan Narayanan

Stephen Michael Marcus

Edward Dennis Haszto

Brian Helfrich

Alison Schondorf

Yevgenly Lyudovyk

In one embodiment, a semantic classifier input and a corresponding label attributed to the semantic classifier input may be obtained. A determination may be made whether the corresponding label is correct based on logged interaction data. An entry of an adaptation corpus may be generated based on a result of the determination. Operation of the semantic classifier may be adapted based on the adaptation corpus.

Learning from interactions for a spoken dialog system

A method includes steps of indexing a media collection, searching an indexed library and browsing a set of candidate program segments. The step of indexing a media collection creates the indexed library based on a content of the media collection. The step of searching the indexed library identifies the set of candidate program segments based on a search criteria. The step of browsing the set of candidate program segments selects a segment for viewing.

Browsing and retrieval of full broadcast-quality video

Embodiments of the present invention relate to a method and system for providing automated directory assistance with minimum external or operator intervention. A directory listing request may be received from a user. The directory listing request may be recognized and a first search of a database may be conducted for the recognized directory listing request. If more than one match for the recognized directory listing request is found in the database, the user may be prompted to provide at least one of a street address and category information for the recognized directory listing request. A second search of the database may be conducted using at least one of the street address and the category information provided by the user. If a match for the recognized directory listing request is found, a directory listing may be output to the user.

System and method for automatically processing a user's request by an automated assistant

The invention concerns method and system for pre-processing entries in a directory listings. An automated attendant or automated directory listings assistant may use the pre-processed entries. A first directory listings including one or more fields may be received. The one or more fields may be populated with entries including one or more symbol strings. A second directory listings including one or more fields may be received. The one or more fields of the second directory listings may be populated with entries including one or symbol strings. Entries in the one or more fields of the first directory listings may be correlated with entries in the corresponding one or more fields of the second directory listings. Entries, in the one or more fields of the first directory listings, which do not correlate with entries in the corresponding one or more fields of the second directory listings may be identified. The identified entries may be processed using a rule set corresponding to the field in which the entry is located. Based on the rule set, a corresponding confidence level for the processed entries may be determined. The processed entries having the corresponding confidence level meeting or exceeding a threshold may be automatically modified. The automatically modified entries may be outputted for processing. In alternative embodiments of the present invention, the processed entries having the corresponding confidence level below the threshold may be marked for operator confirmation.

System and method for pre-processing information used by an automated attendant

The invention concerns a method and apparatus for processing a user's communication. The invention may include receiving a list of recognized symbol strings of one or more recognized entries. The list of recognized symbol strings may include a first similarity score associated with each recognized entry. From each recognized symbol string one or more contiguous sequences of N-symbols may be extracted. One of the extracted contiguous sequences of N-symbols may be matched with at least one stored contiguous sequence of N-symbols from a first database. A preliminary set of symbol strings and associated second similarity scores may be generated. The preliminary set of symbol strings may include one or more stored symbol strings from a second database that correspond to the at least one matched contiguous sequence of N-symbols. A third similarity score associated with the one or more stored symbol strings included in the preliminary set of symbol strings may be computed. A refined set of symbol strings from the preliminary set of symbol strings based on the computed third similarity score may be output.

Method and apparatus for automatically processing a user's communication

A network resource system includes a first server which can communicate with a client computer. The first server produces a speech signal representing speech from a user at the client computer, and context information which indicates the semantic context of the user's speech and a predefined format in which data are returned to the first server. A network knowledge server is in communication with and separated from the first server. The network knowledge server returns to the first server a text structure having one or more fields corresponding to the predefined format. The first server uses data from the one or more fields to determine a response to the user's speech.

Natural language knowledge servers as network resources

A method of using at least one natural language query to retrieve information from one or more data resources and further performing a requested action using the retrieved information is disclosed. At least one natural language query directed to retrieving particular information is received. At least one object from the natural language query is extracted. The relationship between each of the at least one extracted objects is determined. A semantic representation is created from the at least one extracted objects. The semantic representation is compared to a knowledge structure. The knowledge structure is comprised of one or more grammars which are extracted from a plurality of data resources. The semantic representations are matched to the grammar. A database query is generated based on the matched objects. The query is applied to one or more of the data resources and information is retrieved. The requested action is then performed using the retrieved information.

Method of using a natural language interface to retrieve information from one or more data resources

Growing community of inventors

Livingston, NJ, United States of America

Esther Levin