Microsoft Technology Licensing, LLC

Other

Xiaodong He

Jianfeng Gao

Li Deng

Jianshu Chen

Alejandro Acero

Ye-Yi Wang

Yelong Shen

Dong Yu

Xinying Song

Prabhdeep Singh

Larry Paul Heck

Chenlei Guo

Geoffrey G Zweig

Sanaz Ahari

Jian Wu

Alnur Ali

Bodo Von Billerbeck

Ji He

Po-Sen Huang

Shasha Xie

Alex Smola

Zichao Yang

John Carlton Platt

Dilek Zeynep Hakkani-Tur

Ruhi Sarikaya

Qiang Fu

Yifan Gong

Yi Chen

Michael Gamon

Julian James Odell

Xiaodong Liu

Ruofei Zhang

Min Chu

Li Jiang

Mei-Yuh Hwang

Patrick Pantel

Wei Zhang

Xiaolong Li

Kristina Nikolova Toutanova

Kaisheng N Yao

LuMing Wang

Zijian Zheng

Wen-tau Yih

Brian D Remick

Lihong Li

Margaret Ann Mitchell

Xiujun Li

Guowei Liu

Anoop Deoras

Patrick Nguyen

Saurabh Gupta

Mingyang Zhao

Divya Jetley

Gregory T Buehrer

Alex Acero

Jianchang Mao

Byungki Byun

Yun-Nung Chen

Lin Xiao

Jennifer Ann Gillenwater

Shiun-Zu Kuo

Takako Aikawa

Bin Zhang

Qiang Lou

Paul Smolensky

Masaki Itagaki

Kevin E Feige

Mei Yang

Yunhong Zhou

Edward Thiele

Mohammed Aatif Ali

Rupesh Kumar Srivastava

Marcus Gois

Stephen Friesen

Hamid Palangi

Forrest Iandola

Shihao Ji

Moontae Lee

Amittai Axelrod

Brendan W L Clement

Bochen Jin

Yaodong Zhang

Sandeep P Solanki

Megan Riley

Hanjun Xian

Yilei Zhang

Kevin Duh

Gregoire Mesnil

Hao Fang

In some examples, a computing device refines feature information of query text. The device repeatedly determines attention information based at least in part on feature information of the image and the feature information of the query text, and modifies the feature information of the query text based at least in part on the attention information. The device selects at least one of a predetermined plurality of outputs based at least in part on the refined feature information of the query text. In some examples, the device operates a convolutional computational model to determine feature information of the image. The device network computational models (NCMs) to determine feature information of the query and to determine attention information based at least in part on the feature information of the image and the feature information of the query. Examples include a microphone to detect audio corresponding to the query text.

Multi-stage image querying

A processing unit can operate a first recurrent computational model (RCM) to provide first state information and a predicted result value. The processing unit can operating a first network computational model (NCM) to provide respective expectation values of a plurality of actions based at least in part on the first state information. The processing unit can provide an indication of at least one of the plurality of actions, and receive a reference result value, e.g., via a communications interface. The processing unit can train the first RCM based at least in part on the predicted result value and the reference result value to provide a second RCM, and can train the first NCM based at least in part on the first state information and the at least one of the plurality of actions to provide a second NCM.

Multi-model controller

Technologies pertaining to slot filling are described herein. A deep neural network, a recurrent neural network, and/or a spatio-temporally deep neural network are configured to assign labels to words in a word sequence set forth in natural language. At least one label is a semantic label that is assigned to at least one word in the word sequence.

Assignment of semantic labels to a sequence of words using neural network architectures

A processing unit can determine multiple representations associated with a statement, e.g., subject or predicate representations. In some examples, the representations can lack representation of semantics of the statement. The computing device can determine a computational model of the statement based at least in part on the representations. The computing device can receive a query, e.g., via a communications interface. The computing device can determine at least one query representation, e.g., a subject, predicate, or entity representation. The computing device can then operate the model using the query representation to provide a model output. The model output can represent a relationship between the query representations and information in the model. The computing device can, e.g., transmit an indication of the model output via the communications interface. The computing device can determine mathematical relationships between subject representations and attribute representations for multiple statements, and determine the model using the relationships.

Computational-model operation using multiple subject representations

A processing unit can acquire datasets from respective data sources, each having a respective unique data domain. The processing unit can determine values of a plurality of features based on the plurality of datasets. The processing unit can modify input-specific parameters or history parameters of a computational model based on the values of the features. In some examples, the processing unit can determine an estimated value of a target feature based at least in part on the modified computational model and values of one or more reference features. In some examples, the computational model can include neural networks for several input sets. An output layer of at least one of the neural networks can be connected to the respective hidden layer(s) of one or more other(s) of the neural networks. In some examples, the neural networks can be operated to provide transformed feature value(s) for respective times.

Training and operation of computational models

A processing unit can successively operate layers of a multilayer computational graph (MCG) according to a forward computational order to determine a topic value associated with a document based at least in part on content values associated with the document. The processing unit can successively determine, according to a reverse computational order, layer-specific deviation values associated with the layers based at least in part on the topic value, the content values, and a characteristic value associated with the document. The processing unit can determine a model adjustment value based at least in part on the layer-specific deviation values. The processing unit can modify at least one parameter associated with the MCG based at least in part on the model adjustment value. The MCG can be operated to provide a result characteristic value associated with test content values of a test document.

Training and operating multi-layer computational models

A deep learning network is trained to automatically analyze enterprise data. Raw data from one or more global data sources is received, and a specific training dataset that includes data exemplary of the enterprise data is also received. The raw data from the global data sources is used to pre-train the deep learning network to predict the results of a specific enterprise outcome scenario. The specific training dataset is then used to further train the deep learning network to predict the results of a specific enterprise outcome scenario. Alternately, the raw data from the global data sources may be automatically mined to identify semantic relationships there-within, and the identified semantic relationships may be used to pre-train the deep learning network to predict the results of a specific enterprise outcome scenario.

Leveraging global data for enterprise data analytics

Techniques for providing a people recommendation system for predicting and recommending relevant people (or other entities) to include in a conversation based on contextual indicators. In an exemplary embodiment, email recipient recommendations may be suggested based on contextual signals, e.g., project names, body text, existing recipients, current date and time, etc. In an aspect, a plurality of properties including ranked key phrases are associated with profiles corresponding to personal entities. Aggregated profiles are analyzed using first- and second-layer processing techniques. The recommendations may be provided to the user reactively, e.g., in response to a specific query by the user to the people recommendation system, or proactively, e.g., based on the context of what the user is currently working on, in the absence of a specific query by the user.

Contextual people recommendations

A computer-implemented technique is described herein for detecting actionable items in speech. In one manner of operation, the technique can include receiving utterance information that expresses at least one utterance made by one participant of a conversation to at least one other participant of the conversation. The technique can also include converting the utterance information into recognized speech information and using a machine-trained model to recognize at least one actionable item associated with the recognized speech information. The technique can also include performing at least one computer-implemented action associated the actionable item(s). The machine-trained model may correspond to a deep-structured convolutional neural network. The technique can produce the machine-trained model using a source environment corpus that is not optimally suited for a target environment in which the model is intended to be applied. The technique can provide adaptation techniques for adapting a source-environment model to better suit the target environment.

Detecting actionable items in a conversation among participants

Systems, methods, and computer-readable media for providing semantically-relevant discovery of solutions are described herein. In some examples, a computing device can receive an input, such as a query. The computing device can process each word of the input sequentially to determine a semantic representation of the input. Techniques and technologies described herein determine a response to the input, such as an answer, based on the semantic representation of the input matching a semantic representation of the response. An output including one or more relevant responses to the request can then be provided to the requestor. Example techniques described herein can apply machine learning to train a model with click-through data to provide semantically-relevant discovery of solutions. Example techniques described herein can apply recurrent neural networks (RNN) and/or long short term memory (LSTM) cells in the machine learning model.

Semantically-relevant discovery of solutions

A system may comprise one or more processors and memory storing instructions that, when executed by one or more processors, configure one or more processors to perform a number of operations or tasks, such as receiving a query or a document, and mapping the query or the document into a lower dimensional representation by performing at least one operational layer that shares at least two disparate tasks.

Representation learning using multi-task deep neural networks

A deep structured semantic module (DSSM) is described herein which uses a model that is discriminatively trained based on click-through data, e.g., such that a conditional likelihood of clicked documents, given respective queries, is maximized, and a condition likelihood of non-clicked documents, given the queries, is reduced. In operation, after training is complete, the DSSM maps an input item into an output item expressed in a semantic space, using the trained model. To facilitate training and runtime operation, a dimensionality-reduction module (DRM) can reduce the dimensionality of the input item that is fed to the DSSM. A search engine may use the above-summarized functionality to convert a query and a plurality of documents into the common semantic space, and then determine the similarity between the query and documents in the semantic space. The search engine may then rank the documents based, at least in part, on the similarity measures.

Dimensionally reduction of linguistics information

Various technologies described herein pertain to training and utilizing a general, statistical framework for modeling translation via Markov random fields (MRFs). An MRF-based translation model can be employed in a statistical machine translation (SMT) system. The MRF-based translation model allows for arbitrary features extracted from a phrase pair to be incorporated as evidence. The parameters of the model are estimated using a large-scale discriminative training approach based on stochastic gradient ascent and an N-best list based expected Bilingual Evaluation Understudy (BLEU) as an objective function.

Training markov random field-based translation models using gradient ascent

An 'Interestingness Modeler' uses deep neural networks to learn deep semantic models (DSM) of 'interestingness.' The DSM, consisting of two branches of deep neural networks or their convolutional versions, identifies and predicts target documents that would interest users reading source documents. The learned model observes, identifies, and detects naturally occurring signals of interestingness in click transitions between source and target documents derived from web browser logs. Interestingness is modeled with deep neural networks that map source-target document pairs to feature vectors in a latent space, trained on document transitions in view of a &#x201c;context&#x201d; and optional &#x201c;focus&#x201d; of source and target documents. Network parameters are learned to minimize distances between source documents and their corresponding &#x201c;interesting&#x201d; targets in that space. The resulting interestingness model has applicable uses, including, but not limited to, contextual entity searches, automatic text highlighting, prefetching documents of likely interest, automated content recommendation, automated advertisement placement, etc.

Modeling interestingness with deep neural networks

Growing community of inventors

Issaquah, WA, United States of America

Xiaodong He