We present a syntax-based statistical translation model. Our model transforms a source-language parse tree into a target-language string by applying stochastic operations at each node. These operations capture linguistic differences such as word order and case marking. Model parameters are estimated in polynomial time using an EM algorithm. The model produces word alignments that are better than those produced by IBM Model 5.

https://faculty.washington.edu/fxia/courses/LING580MT/yamada_2001.pdf

A Syntax-based Statistical Translation Model

A natural language interface control system (206) for operating a plurality of devices (114) consists of a first microphone array (108), a feature extraction module (202) coupled to the first microphone array, and a speech recognition module (204) coupled to the feature extraction module, wherein the speech recognition module utilizes hidden Markov models. The system also comprises a natural language interface module (222) coupled to the speech recognition module (204) and a device interface (210) coupled to the natural language interface module (222), wherein the natural language interface module is for operating a plurality of devices coupled to the device interface based upon non-prompted, open-ended natural language requests from a user.

Natural language interface control system

In embodiments of the present invention improved capabilities are described for controlling a mobile communication facility utilizing ancillary information comprising accepting speech presented by a user using a resident capture facility on the mobile communication facility while the user engages an interface that enables a command mode for the mobile communications facility; processing the speech using a resident speech recognition facility to recognize command elements and content elements; transmitting at least a portion of the speech through a wireless communication facility to a remote speech recognition facility; transmitting information from the mobile communication facility to the remote speech recognition facility, wherein the information includes information about a command recognizable by the resident speech recognition facility and at least one of language, location, display type, model, identifier, network provider, and phone number associated with the mobile communication facility; generating speech-to-text results utilizing the remote speech recognition facility based at least in part on the speech and on the information related to the mobile communication facility; and transmitting the text results for use on the mobile communications facility.

Command and control utilizing ancillary information in a mobile voice-to-speech application

In embodiments of the present invention improved capabilities are described for multiple web-based content category searching for web content on a mobile communication facility comprising capturing speech presented by a user using a resident capture facility on the mobile communication facility; transmitting at least a portion of the captured speech as data through a wireless communication facility to a speech recognition facility; generating speech-to-text results for the captured speech utilizing the speech recognition facility; and transmitting the text results and a plurality of formatting rules specifying how search text may be used to form a query for a search capability on the mobile communications facility, wherein each formatting rule is associated with a category of content to be searched.

Multiple web-based content category searching in mobile search application

In embodiments of the present invention improved capabilities are described for interacting with a mobile communication facility comprising receiving a switch activation from a user to initiate a speech recognition recording session, wherein the speech recognition recording session comprises a voice command from the user followed by the speech to be recognized from the user; recording the speech recognition recording session using a mobile communication facility resident capture facility; recognizing at least a portion of the voice command as an indication that user speech for recognition will begin following the end of the at least a portion of the voice command; recognizing the recorded speech using a speech recognition facility to produce an external output; and using the selected output to perform a function on the mobile communication facility.

Dealing with switch latency in speech recognition

A method and system, which may be implemented by employing a program storage device readable by machine, and tangibly embodying a program of instructions executable by the machine to perform method steps for ensuring robustness of a natural language understanding (NLU) system, includes tagging recognized words of a command input to the NLU system to associate the command with a context, and translating the command to at least one formal command based on the tagged words. A top ranked formal command is determined based on scoring of the tagged recognized words and scoring translations of the at least one formal command. Whether the top ranked formal command is accepted is determined by comparing a feature vector of the top ranked formal command to representations of feature vectors stored in an accept model. The top ranked formal command is executed if accepted and incorrect commands are prevented from execution to provide a robust NLU system.

Method and system for ensuring robustness in natural language understanding

A method and system, which may be implemented by employing a program, perform method steps of a natural language understanding (NLU) system which include tagging, 200, recognized words of a command input to the NLU system to associate the command with a context, and translating, 300, the command to at least one formal command based on the tagged words. A top ranked formal command is determined, 400, based on scoring of the tagged recognized words and scoring translations of the at least one formal command. Whether the top ranked formal command is accepted is determined by comparing a feature vector of the top ranked formal command to representations of feature vectors stored in an accept model. The top ranked formal command is executed, 500, if accepted and incorrect commands are prevented from execution.

Kyle A Jamieson

Papers

Method and system for ensuring robustness in natural language understanding

Natural language understanding system for command execution