Nuance Communications, Inc.

Taimed Biologics, Inc.

Taimed Biologies, Inc.

Bristol-Myers Squibb Compnay

Universitéde Montreal

Jean-Francois Lavallee

R Michael Lawrence

Edward H Ruediger

Shoshana L Posy

Daniel H Deon

Jacques Banville

Michael Matthew Miller

Brent Richard Stranix

Marc Gagnon

Real Tremblay

Simona Gandrabur

Valérie Perron

Kenneth W D Smith

Guy Milot

Pancras C Wong

Alain Martel

Julia Guy

Nicolas Leberre

Dominik Herbart

Chandra Panchal

Jacques-Olivier Goussard

Richard J Beaufort

Francois Tremblay

Chandra J Panchal

Dietmar Alfred Seiffert

Aspects of the disclosure are directed to natural language processing or natural language understanding and may include a determination of a probabilistic or probability-based ranking of potential results. For example, natural language input may be received such as speech or text. Natural language processing may be performed to determine one or more potential results for the input. A pairwise classifier may be used to determine a score for element pairs in the potential results. Based on the scores, probabilities for the element pairs may be determined. Based on the probabilities for the element pairs, further probabilities may be determined such as by estimating the probability that a current result is the top rank or best choice. Based on the estimated probabilities that the current result is the top rank or best choice, a ranking may be determined, which may form the basis for natural language understanding output.

Probabilistic ranking for natural language understanding

Aspects of the disclosure are directed to natural language processing. An input interface of a computing device receives input (e.g., speech input) and generates a digital signal corresponding to that input. Text corresponding to the digital signal is obtained, and the text is processed using each of a context-free and a context-specific linguistic model to generate linguistic processing results for that text. The text and linguistic processing results may be processed using a NLU model to generate an NLU recognition result corresponding to the input received at the input interface. The text and the linguistic processing results may also be annotated and used to train a NLU model. The linguistic processing results may relate to, e.g., the tokenization of portions of the text, the normalization of portions of the text, sequences of normalizations for portions of the text, and rankings and prioritization of the linguistic processing results.

Processing natural language text with context-specific linguistic model

Multiple natural language understanding (NLU) interpretation selection models may be generated. The NLU interpretation selection models may include a generic NLU interpretation selection model that is not specialized for a specific set of NLU interpretations type and one or more specialized NLU interpretation selection models, each of which may be specific to a particular set of NLU interpretations type. The specialized NLU interpretation selection model(s) may be utilized to process natural language input data comprising data corresponding to their respective sets of NLU interpretations type(s). The generic NLU interpretation selection model may be utilized to process natural language input data comprising data that does not correspond to the sets of NLU interpretations type(s) associated with the specialized NLU interpretation selection model(s).

Semantic re-ranking of NLU results in conversational dialogue applications

Disclosed methods and systems are directed to task switching in dialog processing. The methods and systems may include activating a primary task, receiving, one or more ambiguous natural language commands, and identifying a first candidate task for each of the one or more ambiguous natural language commands. The methods and system may also include identifying, for each of the one or more ambiguous natural language commands and based on one or more rules, a second candidate task of the plurality of tasks corresponding to the ambiguous natural language command, determining whether to modify at least one of the one or more rules-based task switching rules based on whether a quality metric satisfies a threshold quantity, and when the second quality metric satisfies the threshold quantity, changing the task switching rule for the corresponding candidate task from a rules-based model to the optimized statistical based task switching model.

Task switching in dialogue processing

A method for refining a search is provided. Embodiments may include receiving a first speech signal corresponding to a first utterance and receiving a second speech signal corresponding to a second utterance, wherein the second utterance is a refinement to the first utterance. Embodiments may also include determining a first quantity of search results based upon the first speech signal information and determining a second quantity of search results based upon the second speech signal information. Embodiments may also include comparing at least one of the first quantity of search results and the second quantity of search results with a third quantity of search results and determining an information gain from the comparison.

Method for refining a search

A method for refining a search is provided. Embodiments may include receiving a first speech signal corresponding to a first utterance and receiving a second speech signal corresponding to a second utterance, wherein the second utterance is a refinement to the first utterance. Embodiments may also include identifying information associated with the first speech signal as first speech signal information and identifying information associated with the second speech signal as second speech signal information. Embodiments may also include determining a first quantity of search results based upon the first speech signal information and determining a second quantity of search results based upon the second speech signal information. Embodiments may also include comparing at least one of the first quantity of search results and the second quantity of search results with a quantity of search results from a combination of information of the first and second signals and determining an information gain from the comparison.

The present invention provides HIV protease inhibitors of formulas I, IA, IB, Ib or II, or pharmaceutically acceptable salts thereof, wherein Rmay be, for example, 2-pyridyl-CH&#x2014;, 3-pyridyl-CH&#x2014;, 4-pyridyl-CH&#x2014;, a sulfonyl group as described in the formulas herein including benzenesulfonyl or thiophenesulfonyl groups, R&#x2014;CO)&#x2014;, Rbeing selected from the group consisting of piperonyl, 2-pyranzinyl (unsubstituted or substituted with H, or an alkyl of 1 to 4 carbon atoms) or a picolylamine group as described herein, wherein R3 may be, for example, a phenyl group or diphenylmethyl group as described herein, and wherein Cx may be, for example, COOH, CONRR, CHOH or CHOR.

Protease inhibitors

The present invention provides HIV protease inhibitors of formulas I, IA, IB, Ib or II, or pharmaceutically acceptable salts thereof, wherein Rmay be, for example, 2-pyridyl-CH&#x2014;, 3 -pyridyl-CH&#x2014;, 4-pyridyl-CH&#x2014;, a sulfonyl group as described in the formulas herein including benzenesulfonyl or thiophenesulfonyl groups, R&#x2014;CO&#x2014;, Rbeing selected from the group consisting of piperonyl, 2-pyrazinyl (unsubstituted or substituted with H, or an alkyl of 1 to 4 carbon atoms) or a picolylamine group as described herein, wherein R3 may be, for example, a phenyl group or diphenylmethyl group as described herein, and wherein Cx may be, for example, COOH, CONRR, CHOH or CHOR.

Growing community of inventors

Montreal, Canada

Jean-Francois Lavallee