Amazon Technologies, Inc.

Nuance Communications, Inc.

Tagyoung Chung

Arindam Mandal

Real Tremblay

Raefer Christopher Gabriel

Dilek Zeynep Hakkani-Tur

Yang Liu

Angeliki Metallinou

Serge Robillard

Jerome Tremblay

Premkumar Natarajan

Jing Huang

Alina Andreevskaia

Anjali Yuan Narayan-Chen

Shereen Oraby

Jiao Sun

Jackson Liscombe

Chien-wei Lin

Rohit Prasad

Nikko Strom

Amitabh Saikia

Prakash Krishnan

Suranjit Adhikari

Rahul Goel

Chandra Prakash Khatri

Govindarajan Sundaram Thattai

Anushree Venkatesh

Behnam Hedayatnia

Devesh Mohan Pandey

Aishwarya Naresh Reganti

Anish Acharya

Qing Liu

Meyyappan Sundaram

Shanchan Wu

Shachi Paul

Sanghyun Yi

Shuyang Gao

Nanyung Peng

Alessandra Cervone

Nanyun Peng

Shubhra Chandra

Sridhar Yadav Manoharan

Ankita De

Gabriel Forgues

In accordance with one disclosed method, first data representing first text may be processed using a first machine learning model configured to generate second data representing an explanation as to why the first text is humorous. The second data may be processed, together with the first data, by a second machine learning model configured to generate a value indicating that the first data and the second data correspond to a pun. A device may be caused to take at least a first action based at least in part on the value.

Virtual assistant humor management

In accordance with one disclosed method, first data representing one or more first keywords may be processed by at least one first component to determine a first pair of words suitable for generating a pun. The first pair of words may then be processed using a first machine learning model configured to generate an output pun based at least in part on one or more input keywords and an input word pair such that the output pun is contextually related to the one or more input keywords. A first pun that is contextually related to the one or more first keywords may be received from the first machine learning model, and a first device may be caused to output a representation of the first pun.

Techniques for facilitating natural language interactions with visual interactive content are described. During a build time, a system analyzes various websites and applications relating to a particular user goal to understand website and application navigation and information relating to the user goal. The learned information is used to store configuration data. During runtime, when a user request performance of an action, the system engages in a dialog with the user to complete the user's goal. The system uses the stored configuration data to determine actions to be performed at a website or application to complete the user's goal, and determines system responses to present to the user to facilitate completion of the goal. Such system responses may request information from the user, may inform the user of information displayed at the website or application, etc.

Natural language interactions with interactive visual content

A dialog generator receives data corresponding to desired dialog, such as application programming interface (API) information and sample dialog. A first model corresponding to an agent simulator and a second model corresponding to a user simulator take turns creating a plurality of dialog outlines of the desired dialog. The dialog generator may determine that one or more additional APIs are relevant to the dialog and may create further dialog outlines related thereto. The dialog outlines are converted to natural dialog to generate the dialog.

Goal-oriented dialog generation using dialog template, API, and entity data

A dialog manager receives text data corresponding to a dialog with a user. Entities represented in the text data are identified. Context data relating to the dialog is maintained, which may include prior dialog, prior API calls, user profile information, or other data. Using the text data and the context data, an N-best list of one or more dialog models is selected to process the text data. After processing the text data, the outputs of the N-best models are ranked and a top-scoring output is selected. The top-scoring output may be an API call and/or an audio prompt.

Goal-oriented dialog system

A system that can engage in a dialog with a user may select a system response to a user input based on how the system estimates a user may respond to a potential system response. Models may be trained to evaluate a potential system response in view of various available data including dialog history, entity data, etc. Each model may score the potential system response for various qualitative aspects such as whether the response is likely to be comprehensible, on-topic, interesting, likely to lead to the dialog continuing, etc. Such scores may be combined to other scores such as whether the potential response is coherent or engaging. The models may be trained using previous dialog/chatbot evaluation data. At runtime the scores may be used to select a system response to a user input as part of the dialog.

Dialog response generation

Aspects described herein provide quality assurance checks for improving the construction of natural language understanding grammars. An annotation module may obtain a set of annotations for a set of text samples based, at least in part, on an ontology and a grammar. A quality assurance module may automatically perform one or more quality assurance checks on the set of annotations, the ontology, the grammar, or combinations thereof. The quality assurance module may generate a list of flagged annotations during performance of a quality assurance check. The list of flagged annotations may be presented at an annotation review interface displayed at a display device. One of the flagged annotations may be selected and presented at an annotation interface displayed at the display device. Responsive to presentation of the flagged annotation, the ontology, the grammar, the flagged annotation selected, or combinations thereof may be updated based on user input received.

Automated quality assurance checks for improving the construction of natural language understanding systems

Natural language understanding (NLU) engines perform better when they are trained with large amounts of data. However, a large amount of data is not always available. Embodiments of the present invention overcome this problem by generating annotated data for use in a NLU system. An example embodiment generates annotated data by parsing an input annotated phrase, generating a syntactic tree reflecting a grammatical structure of the parsed phrase, and generating one or more alternative versions of the input annotated phrase based on the syntactic tree. Alignment between expressions and corresponding annotations in the annotated phrase are preserved in the one or more alternative versions generated to ensure intention of the input annotated phrase is maintained.

Syntactic parser assisted semantic rule inference

Growing community of inventors

Sunnyvale, CA, United States of America

Tagyoung Chung