Abstract: Described herein are systems and methods that provide a natural language processing system (NLPS) that employs compressed word embeddings. An auto-encoder that includes encoder circuitry and decoder circuitry can be used to produce the compressed word embeddings. The decoder circuitry is trained to decompress the word embeddings with reduced or minimal differences between the original uncompressed word embeddings and the corresponding decompressed word embeddings. One or more parameters of the trained decoder circuitry are transferred to the NLPS, where the NLPS is then trained using the compressed word embeddings to improve the correctness of the responses or actions determined by the NLPS.

Abstract: A machine reading comprehension system (MRCS) can analyze a larger-sized document that includes multiple pages to predict an answer to a query. For example, the document can have two, five, tens, or hundreds of pages. The MRCS divides the document into multiple sections with each section including a portion of the document. Each section is processed separately by one or more processing circuitries to determine a score for that section. The score indicates how related the section is to the query and/or a probability that the section provides a possible answer to the query. Once all of the sections have been analyzed, the sections are ranked by their scores and a subset of the ranked sections are processed again to determine a predicted answer to the query.

Abstract: A machine reading comprehension system (MRCS) can analyze a larger-sized document that includes multiple pages to predict an answer to a query. For example, the document can have two, five, tens, or hundreds of pages. The MRCS divides the document into multiple sections with each section including a portion of the document. Each section is processed separately by one or more processing circuitries to determine a score for that section. The score indicates how related the section is to the query and/or a probability that the section provides a possible answer to the query. Once all of the sections have been analyzed, the sections are ranked by their scores and a subset of the ranked sections are processed again to determine a predicted answer to the query.

Abstract: This document relates to techniques for addressing disruptions that prevent applications from receiving user input, prevent users from providing input to an application, and/or prevents or impacts users from receiving application output. One example method involves detecting a disruption to an interactive application during interaction by a user with the interactive application, generating automated user inputs, and providing the automated user inputs to the interactive application during the disruption to the interactive application.

Abstract: This document relates to techniques for addressing disruptions that prevent applications from receiving user input, prevent users from providing input to an application, and/or prevents or impacts users from receiving application output. One example method involves detecting a disruption to an interactive application during interaction by a user with the interactive application, generating automated user inputs, and providing the automated user inputs to the interactive application during the disruption to the interactive application.

Abstract: This document relates to techniques for addressing disruptions that prevent applications from receiving user input, prevent users from providing input to an application, and/or prevents or impacts users from receiving application output. One example method involves detecting a disruption to an interactive application during interaction by a user with the interactive application, generating automated user inputs, and providing the automated user inputs to the interactive application during the disruption to the interactive application.

Abstract: A spoken dialogue system includes a spoken language understanding apparatus. The spoken language understanding apparatus can include an intent apparatus and a selection apparatus. The intent apparatus is configured to determine if a query comprises a global command, to determine if an intent associated with a query is or is not included in a domain that is supported by the spoken dialogue system, to determine if a query comprises a confirmation type, to tag one or more entities in a query, and to determine an intent probability distribution and a domain probability distribution that is associated with a query. When the query includes an entity that is included in two or more possible entities, the selection apparatus is configured to provide a score for each of the two or more possible entities.

Abstract: This document relates to techniques for addressing disruptions that prevent applications from receiving user input, prevent users from providing input to an application, and/or prevents or impacts users from receiving application output. One example method involves detecting a disruption to an interactive application during interaction by a user with the interactive application, generating automated user inputs, and providing the automated user inputs to the interactive application during the disruption to the interactive application.

Abstract: A machine reading comprehension system (MRCS) can analyze a larger-sized document that includes multiple pages to predict an answer to a query. For example, the document can have two, five, tens, or hundreds of pages. The MRCS divides the document into multiple sections with each section including a portion of the document. Each section is processed separately by one or more processing circuitries to determine a score for that section. The score indicates how related the section is to the query and/or a probability that the section provides a possible answer to the query. Once all of the sections have been analyzed, the sections are ranked by their scores and a subset of the ranked sections are processed again to determine a predicted answer to the query.

Abstract: Described herein are systems and methods that provide a natural language processing system (NLPS) that employs compressed word embeddings. An auto-encoder that includes encoder circuitry and decoder circuitry can be used to produce the compressed word embeddings. The decoder circuitry is trained to decompress the word embeddings with reduced or minimal differences between the original uncompressed word embeddings and the corresponding decompressed word embeddings. One or more parameters of the trained decoder circuitry are transferred to the NLPS, where the NLPS is then trained using the compressed word embeddings to improve the correctness of the responses or actions determined by the NLPS.

Abstract: A spoken dialogue system includes a spoken language understanding apparatus. The spoken language understanding apparatus can include an intent apparatus and a selection apparatus. The intent apparatus is configured to determine if a query comprises a global command, to determine if an intent associated with a query is or is not included in a domain that is supported by the spoken dialogue system, to determine if a query comprises a confirmation type, to tag one or more entities in a query, and to determine an intent probability distribution and a domain probability distribution that is associated with a query. When the query includes an entity that is included in two or more possible entities, the selection apparatus is configured to provide a score for each of the two or more possible entities.