At&t Intellectual Property I, L.p.

Amazon Technologies, Inc.

At+t Corp.

Vui, Inc.

Nuance Communications, Inc.

Giuseppe Di Fabbrizio

Bernard S Renger

Narendra Kumar Gupta

David Crawford Gibbon

Benjamin J Stern

Charles Alfred Lewis

Srinivas Bangalore

Dilek Zeynep Hakkani-Tur

Gokhan Tur

Mazin G Rahim

Amanda Joy Stent

Nils Klarlund

Rittwik Jana

Bin Wei

Jay Gordon Wilpon

Yih-Farn Robin Chen

Evgeny Stepanov

Phil C Frank

Lee Begeja

Behzad Shahraray

Zhu Liu

Mazin E Gilbert

Junlan Feng

Giuseppe Riccardi

Serban Jora

Juergen Schroeter

Robert Elias Schapire

Barbara B Hollister

Shishir Sridhar Bharathi

Dawn L Dutton

Shardul Naithani

Purvank Dhimantkumar Patel

Giuliano Tortoreto

Andrea Basso

Alistair D Conkie

John Ruckart

Thomas Joseph Killian

Charles Douglas Blewett

Karrie Jo Hanson

Gerald Michael Karam

Donnie Henderson

Lambert Leo Mathias

Sumedha Arvind Kshirsagar

John Daniel Thimsen

David Kormann

Enrico Bocchieri

Thomas Kirk

Ying Shi

Wei Ting Chen

Silke Maren Witt-Ehsani

Vikas Jain

Shamitha Somashekar

Ping-Fai Yang

Gregory T Vesonder

Hailong Sun

Douglas Keith Trotman

Tudor Toma

Mehool Patel

Benjamin Edward Lambert

Ling Hu

Giovanni De Toni

A method includes receiving data characterizing a query for information associated with a first item of a plurality of items in an item catalog. The method also includes determining an attribute of the first item. The determining can be performed using a predictive model trained using question-answer pair data associated with a portion of the plurality of items. The portion can include a second item. The method can further include determining an attribute value of the attribute using a mapping of attributes and attribute values associated with the plurality of items in the item catalog. The method can also include providing, as an answer to the query, a characterization of the attribute value. Related systems, methods, apparatus, and computer readable mediums are also described.

Question-answer expansion

A method includes receiving data characterizing historical user interaction with a search engine associated with a plurality of items, the received data including a first search query and a first item name selected by a user in response to receiving a result of a search of the first search query; training, using the received data, a model that maps item names to referring expressions, the training including using the first item name selected by the user as an input to the model and the first search query as a supervisory signal to the model; and providing the model. Related apparatus, systems, techniques, and articles are also described.

Referring expression generation

A method includes receiving data characterizing an utterance of a query associated with a tenant; providing, to an automated speech recognition engine, the received data and a profile selected from a plurality of profiles based on the tenant, the profile configuring the automated speech recognition engine to process the received data; receiving, from the automated speech recognition engine, a text string characterizing the query; and processing, via an ensemble of natural language agents configured based on the tenant, the text string characterizing the query to determine a textual response to the query, the textual response including at least one word from a first lexicon associated with the tenant. Related systems, methods, apparatus, and computer readable mediums are also described.

Multi-modal conversational agent platform

Dialog visualizations are created to enable analysis of interactions between a user and a speech recognition system used to implement user commands. Spoken commands from the user may be classified, along with system responses to the spoken commands, to enable aggregation of communication exchanges that form dialog. This data may then be used to create a dialog visualization. The dialog visualization may enable an analyst to visually explore different branches of the interactions represented in the dialog visualization. The dialog visualization may show a trajectory of the dialog, which may be explored in an interactive manner by the analyst.

Dialog visualization

Features are disclosed for processing and interpreting natural language, such as interpretations of user utterances, in multi-turn dialog interactions. Context information regarding interpretations of user utterances and system responses to the user utterances can be maintained. Subsequent user utterances can be interpreted using the context information, rather than being interpreted without context. In some cases, interpretations of subsequent user utterances can be merged with interpretations of prior user utterances using a rule-based framework. Rules may be defined to determine which interpretations may be merged and under what circumstances they may be merged.

Context interpretation in natural language processing using previous dialog acts

A method and apparatus for processing at least one information feed are disclosed. For example, the method receives at least one content via at least one automated feed. The method associates the at least one content to one or more geographical locations on a map, wherein the one or more geographical locations are determined from the at least one content. The method then presents an access to the at least one content to a user via the map.

Method and apparatus for providing geospatial and temporal navigation

A speech-based system is configured to interact with a user through speech to determine intents and goals of the user. The system may analyze multiple dialog turns in order to determine and fully define a goal that the user is trying to express. Each dialog turn comprises a user utterance. Each dialog turn may also comprise a system speech response. In order to evaluate the performance of the system, logged data is analyzed to identify goal segments within the logged data, where a goal segment is a sequence of dialog turns that relate to a corresponding user goal. A subset of the dialog turns is annotated manually to delineate goal segments. A predictive model is then constructed based on the manually annotated goal segments. The predictive model is then used to identify goal segments formed by additional dialog turns.

Goal segmentation in speech dialogs

A machine-readable medium may include a group of reusable components for building a spoken dialog system. The reusable components may include a group of previously collected audible utterances. A machine-implemented method to build a library of reusable components for use in building a natural language spoken dialog system may include storing a dataset in a database. The dataset may include a group of reusable components for building a spoken dialog system. The reusable components may further include a group of previously collected audible utterances. A second method may include storing at least one set of data. Each one of the at least one set of data may include ones of the reusable components associated with audible data collected during a different collection phase.

Library of existing spoken dialog data for use in generating new natural language spoken dialog systems

Features are disclosed for processing user utterances and applying user-supplied corrections to future user utterances. If a user utterance is determined to relate to a speech processing error that occurred when processing a previous utterance, information about the error or a correction thereto may be stored. Such information may be referred to as correction information. Illustratively, the correction information may be stored in a skip list. Subsequent utterances may be processed based at least partly on the correction information. For example, speech processing results generated from processing subsequent utterances that include a term associated with the error may be removed or re-scored in order to reduce or prevent the chance that an error will be repeated.

Speech processing using skip lists

Concepts and technologies are disclosed herein for managing vendor inventory information and shopping navigation routes based upon shopping list contents. A server computer can execute a shopping management service. A shopping list is obtained at the server computer. The server computer obtains location data indicating a geographic location of the user device and identifies, based upon the location data, a vendor having an inventory comprising the item. The server computer generates a navigation route comprising a stop at a vendor location associated with the vendor, and provides the navigation route to the user device. The server computer can monitor purchases of items on the shopping list, update the shopping list, and update the navigation route. The server computer also can provide suggestions to the user device based upon items in the shopping list.

Managing vendor inventory information and shopping navigation routes based upon shopping list contents

Disclosed are systems, methods and computer-readable media for enabling speech processing in a user interface of a device. The method includes receiving an indication of a field and a user interface of a device, the indication also signaling that speech will follow, receiving the speech from the user at the device, the speech being associated with the field, transmitting the speech as a request to public, common network node that receives and processes speech, processing the transmitted speech and returning text associated with the speech to the device and inserting the text into the field. Upon a second indication from the user, the system processes the text in the field as programmed by the user interface. The present disclosure provides a speech mash up application for a user interface of a mobile or desktop device that does not require expensive speech processing technologies.

System and method of providing speech processing in user interface

A method of generating a summary review of an entity from a set of reviews includes generating a distribution and determining a polarity of the distribution associated with a plurality of aspect ratings based on the set of reviews. The set of reviews are associated with the entity, and the plurality of aspect ratings are associated with an aspect, or feature, of the entity. The method includes selecting an opinion correlated with the polarity from the set of reviews, and generating the summary review, the summary review comprising: a summary statement based on the distribution and the polarity; and the opinion. An apparatus and computer-readable device are also disclosed.

Hybrid review synthesis

A dialog manager and spoken dialog service having a dialog manager generated according to a method comprising selecting a top level flow controller based on application type, selecting available reusable subdialogs for each application part, developing a subdialog for each application part not having an available subdialog and testing and deploying the spoken dialog service using the selected top level flow controller, selected reusable subdialogs and developed subdialogs. The dialog manager capable of handling context shifts in a spoken dialog with a user. Application dependencies are established in the top level flow controller thus enabling the subdialogs to be reusable and to be capable of managing context shifts and mixed initiative dialogs.

System and dialog manager developed using modular spoken-dialog components

Growing community of inventors

Florham Park, NJ, United States of America

Giuseppe Di Fabbrizio