International Business Machines Corporation

Nuance Communications, Inc.

Ruhi Sarikaya

Yuqing Gao

Bhuvana Ramabhadran

Michael Alan Picheny

Alper Buyuktosunoglu

Jiri Navratil

Osamuyimen Stewart

Pradip Bose

David Nahamoo

Xiaoqiao Meng

David M Lubensky

Vaibhava Goel

Canturk Isci

Ossama S Emam

Mark Edward Epstein

Paul Joseph Vozila

Salim Estephan Roukos

Stanley S Chen

Stephen Mingyu Chu

Imed Zitouni

Maximilian Bisani

Hakan Erdogan

Suleyman Serdar Kozat

Rèal Tremblay

Yi Su

Yonggang Deng

Jeff Kephart

David Eubensky

Brian Edward Doorenbos Kingsbury

Operation of an automated dialog system is described using a source language to conduct a real time human machine dialog process with a human user using a target language. A user query in the target language is received and automatically machine translated into the source language. An automated reply of the dialog process is then delivered to the user in the target language. If the dialog process reaches an initial assistance state, a first human agent using the source language is provided to interact in real time with the user in the target language by machine translation to continue the dialog process. Then if the dialog process reaches a further assistance state, a second human agent using the target language is provided to interact in real time with the user in the target language to continue the dialog process.

Machine translation (MT) based spoken dialog systems customer/machine dialog

A language processing application employs a classing function optimized for the underlying production application context for which it is expected to process speech. A combination of class based and word based features generates a classing function optimized for a particular production application, meaning that a language model employing the classing function uses word classes having a high likelihood of accurately predicting word sequences encountered by a language model invoked by the production application. The classing function optimizes word classes by aligning the objective of word classing with the underlying language processing task to be performed by the production application. The classing function is optimized to correspond to usage in the production application context using class-based and word-based features by computing a likelihood of a word in an n-gram and a frequency of a word within a class of the n-gram.

Word classing for language modeling

Techniques for monitoring a set of one or more event counters of application execution are provided. The techniques include constructing a virtual performance monitoring counter (VPMC) layer as a unified abstraction of a physical performance monitoring counter (PMC) architecture, and incorporating one or more programming interfaces (PIs) in connection with the virtual performance monitoring counter, wherein the one or more programming interfaces facilitate simultaneous access and data monitoring across a set of one or more event counters.

Virtualized abstraction with built-in data alignment and simultaneous event monitoring in performance counter based application characterization and tuning

A method of identifying and using side information available to statistical machine translation systems within an enterprise setting, the method including extracting user-specific interaction and non-interaction-based information from at least one corresponding database within the enterprise for each of a plurality of users, aggregating the user-specific interaction and non-interaction based information from a plurality of users, by using a processor on a computer, to tune and adapt background translation and language models, and updating all relevant models within the enterprise after user activity based on the tuned and adapted translation and language models.

Machine translation with side information

A method of generating a statistical machine translation database through a game in which a monolingual structure is provided to a plurality of players. A first translation attempt is received from each of the plurality of players. The first translation attempt from each of the plurality of players is compared. Feedback is provided to each of the plurality of players and the attempts are received and compared to provide feedback to iteratively converge subsequent translations from each of the plurality of players into a final translated structure.

Game based method for translation data acquisition and evaluation

A translation method and system include a recognition engine having a plurality of models each being employed to decode a same utterance to provide an output. A model combiner is configured to assign probabilities to each model output and configured to assign weights to the outputs of the plurality of models based on the probabilities to provide a best performing model for the context of the utterance.

Model weighting, selection and hypotheses combination for automatic speech recognition and machine translation

A system and method for training a statistical machine translation model and decoding or translating using the same is disclosed. A source word versus target word co-occurrence matrix is created to define word pairs. Dimensionality of the matrix may be reduced. Word pairs are mapped as vectors into continuous space where the word pairs are vectors of continuous real numbers and not discrete entities in the continuous space. A machine translation parametric model is trained using an acoustic model training method based on word pair vectors in the continuous space.

Machine translation in continuous space

A method, apparatus and computer instructions is provided for fast semi-automatic semantic annotation. Given a limited annotated corpus, the present invention assigns a tag and a label to each word of the next limited annotated corpus using a parser engine, a similarity engine, and a SVM engine. A rover then combines the parse trees from the three engines and annotates the next chunk of limited annotated corpus with confidence, such that the efforts required for human annotation is reduced.

Method and apparatus for fast semi-automatic semantic annotation

A system and method for restoration of diacritics includes making classification decisions regarding an utterance in accordance with an aggregate of a plurality of information sources in a diacritization model for diacritic restoration. A best diacritic representation is determined for graphemes in the utterance based upon a best match with the diacritization model. A diacritically restored representation of the utterance is output.

System and method for diacritization of text

An objective function is dynamically chosen from a pool of available objective functions, and a prediction model is dynamically chosen from a pool of available prediction models. Points of inflection are determined for the chosen objective function, based on past values of a metric, to obtain a set of equations that can be solved to obtain model parameters associated with the chosen prediction model. The equations are solved to obtain the model parameters, and a future value of the metric is predicted based on (i) at least some of the past values of the metric and (ii) the chosen prediction model, with the obtained associated model parameters.

System and method for predicting hardware and/or software metrics in a computer system using models

Method for fast semi-automatic semantic annotation

A system and method for speech recognition includes generating a set of likely hypotheses in recognizing speech, rescoring the likely hypotheses by using semantic content by employing semantic structured language models, and scoring parse trees to identify a best sentence according to the sentence's parse tree by employing the semantic structured language models to clarify the recognized speech.

Growing community of inventors

Shrub Oak, NY, United States of America

Ruhi Sarikaya