International Business Machines Corporation

Murray Scott Campbell

Chung-Sheng Li

Biplav Srivastava

Wei Zhang

John Richard Smith

Miao Liu

Milind R Naphade

Apostol Ivanov Natsev

Matthew Leon Hill

Yang Yu

Sadhana Kumaravel

Rong Yan

Charu Chandra Aggarwal

Kun-Lung Wu

Philip Shilung Yu

Sriram Kolinjivadi Padmanabhan

Chuang Gan

Yuan-Chi Chang

Min Wang

Shiyu Chang

Mo Yu

Michael James Hind

Shahram Ebadollahi

Kartik Talamadupula

Kshitij P Fadnis

Lexing Xie

Xiaoxiao Guo

Tathagata Chakraborti

Jelena Tesic

Yupeng Gao

Jeanette M Rosenthal

Brian Michael Landry

An artificial intelligence (AI) platform to support random action replay for natural language (NL) learning. A NL conversation is subject to exploration to train a neural network. One or more tuples are leveraged for the training, with each tuple representing an input action, a vector, an output action, and a reward value. An action is sampled from the vector, with the sampling configured to assess a corresponding first gradient. The first gradient is applied to selectively adjust the neural network. As NL input is received and applied to the selectively adjusted neural network, an output corresponding to the NL input is identified and a corresponding action is subject to be executed.

Random action replay for reinforcement learning

An approach to determine the quality of encodings assigned to a word by a word embedding model. The approach may include determining the asymmetry of two embeddings associated with two words from a word embedding model. The asymmetry of the two words from a preexisting evocation dataset may be determined. The asymmetry of the two embeddings may be compared to the asymmetry from the evocation dataset to generate an encoding quality score.

Word embedding quality assessment through asymmetry

Techniques are provided for reinforcement learning software agents enhanced by external data. A reinforcement learning model supporting the software agent may be trained based on information obtained from one or more knowledge stores, such as online forums. The trained reinforcement learning model may be tested in an environment with limited connectivity to an external environment to meet performance criteria. The reinforcement learning software agent may be deployed with the tested and trained reinforcement learning model within an environment to autonomously perform actions to process requests.

Data augmented training of reinforcement learning software agent

A current observation expressed in natural language is received. Entities in the current observation are extracted. A relevant historical observation is retrieved, which has at least one of the entities in common with the current observation. The current observation and the relevant historical observation are combined as observations. The observations and a template list specifying a list of verb phrases to be filled-in with at least some of the entities are input to a neural network, which can output the template list of the verb phrases filled-in with said at least some of the entities. The neural network can include attention mechanism. A reward associated with the neural network's output can be received and fed back to the neural network for retraining the neural network.

Extractive structured prediction in interactive systems

Techniques regarding explanations for artificial intelligence recommendations are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can also comprise a processor, operably coupled to the memory, and that can execute the computer executable components stored in the memory. The computer executable components can include: a combination component that receives a first training dataset comprising first feature vectors, first classes and first explanations, and combines the first classes and the first explanations to produce first augmented labels and a second training dataset that comprises the first feature vectors and the first augmented labels; a classifier, trained on the second training dataset, that analyses second feature vectors and generates second augmented labels; and a decomposing component that decomposes the second augmented labels, using the classifier, to generate second classes and second explanations.

Explanations for artificial intelligence based recommendations

Embodiments of the present invention provide a system for implementing multi-turn dialogs. The system performs a method that includes receiving a series of user utterances, generating a series of responsive system utterances, and labeling the series of responsive system utterances to generate training data for training a dialog management policy. The labeling includes executing a reward function at each turn of a dialog, in which for each turn of the dialog the reward function is configured to output a reward value that is based at least in part on an accuracy of the responsive system utterance of the turn and on number of dialog turns elapsed.

Dialog agent for conducting task-oriented computer-based communications

Interoperability is enabled between participants in a network by determining values associated with a value metric defined for at least a portion of the network. Information flow is directed between two or more of the participants based at least in part on semantic models corresponding to the participants and on the values associated with the value metric. The semantic models may define interactions between the participants and define at least a portion of information produced or consumed by the participants. The determination of the values and the direction of the information flow may be performed multiple times in order to modify the one or more value metrics. The direction of information flow may allow participants to be deleted from the network, may allow participants to be added to the network, or may allow behavior of the participants to be modified.

Enabling interoperability between participants in a network

Improved decision support techniques are disclosed. For example, a technique for processing transactional data for use in accordance with a decision support operation comprises the following steps/operations. The transactional data is transformed into an interim form according to a relative importance of the transactional data to the decision support operation. The transformed data is incrementally analyzed, wherein the incremental analysis comprises applying a successive approximation to the data in the interim form, such that the decision support operation can be incrementally performed based on a transactional load. The technique may further comprise allocating one or more computing resources to incrementally perform the decision support operation.

Decision support methods and apparatus

A computer program product and embodiments of systems are provided for annotating multimedia documents. The computer program product and embodiments of the systems provide for performing manual and automatic annotation.

Method and apparatus for hybrid tagging and browsing annotation for multimedia content

A method and apparatus is disclosed that receives an input narrative in a particular media format, and produces therefrom a multimedia enriched version of the input narrative. In one embodiment, a method is provided for enriching an input narrative with multimedia content, wherein the method includes the step of selectively segmenting the input narrative to form queries pertaining to different portions or elements of the input narrative. The method further comprises retrieving multimedia artifacts from one or more multimedia repositories, wherein each retrieved multimedia artifact is associated with one of the queries, and selecting a subset of the retrieved multimedia artifacts, wherein the subset includes artifacts comprising different types of multimedia content. The input narrative is then combined with respective multimedia artifacts of the subset, in order to provide an enriched and enhanced narrative.

Method and apparatus for automatic multimedia narrative enrichment

Growing community of inventors

Yorktown Heights, NY, United States of America

Murray Scott Campbell