Microsoft Technology Licensing, LLC

Chenguang Zhu

Nanshan Zeng

Xuedong D Huang

Jianfeng Gao

Yu Shi

William Isaac Hinthorn

Jinchao Li

Xiujun Li

Baolin Peng

Liyang Lu

Chunyuan Li

Ruochen Xu

Zheng Chen

Jin Li

Abhishek Gupta

Sudipta Sengupta

Weizhu Chen

Chun Ho Cheung

Jianwen Zhang

A speech module is joint trained with a knowledge module by transforming a first knowledge graph into an acoustic knowledge graph. The knowledge module is trained on the acoustic knowledge graph. Then, the knowledge module is integrated with the speech module to generate an integrated knowledge-speech module. In some instances, the speech module included in the integrated knowledge-speech module is aligned with a language module to generate an optimized speech model configured to leverage acoustic information and acoustic-based knowledge information, along with language information.

Generation of optimized spoken language understanding model through joint training with integrated acoustic knowledge-speech module

A transcription of audio speech included in electronic content associated with a meeting is created by an ASR model trained on speech-to-text data. The transcription is post-processed by modifying text included in the transcription, for example, by modifying punctuation, grammar, or formatting introduced by the ASR model and by changing or omitting one or more words that were included in both the audio speech and the transcription. After the transcription is post-processed, output based on the post-processed transcription is generated in the form of a meeting summary and/or template.

Automated meeting minutes generator

This document relates to machine learning. One example includes a method or technique that can be performed on a computing device. The method or technique can include obtaining a task-semantically-conditioned generative model that has been pretrained based at least on a first training data set having unlabeled training examples and semantically conditioned based at least on a second training data set having dialog act-labeled utterances. The method or technique can also include inputting dialog acts into the semantically-conditioned generative model and obtaining synthetic utterances that are output by the semantically-conditioned generative model. The method or technique can also include outputting the synthetic utterances.

Synthetic data generation for training of natural language understanding models

A language module is joint trained with a knowledge module for natural language understanding by aligning a first knowledge graph with a second knowledge graph. The knowledge module is trained on the aligned knowledge graphs. Then, the knowledge module is integrated with the language module to generate an integrated knowledge-language module.

Generation of optimized knowledge-based language model through knowledge graph multi-alignment

This document relates to machine learning. One example includes a method or technique that can be performed on a computing device. The method or technique can include obtaining a task-adapted generative model that has been tuned using one or more task-specific seed examples. The method or technique can also include inputting dialog acts into the task-adapted generative model and obtaining synthetic utterances that are output by the task-adapted generative model. The method or technique can also include populating a synthetic training corpus with synthetic training examples that include the synthetic utterances. The synthetic training corpus may be suitable for training a natural language understanding model.

Conversational virtual assistance for delivering relevant query solutions is provided. A virtual assistant system comprises various components associated with developing a knowledge database that can be searched for finding documents that fulfill the user's intent. The virtual assistant system further comprises components for receiving a query from a user, extracting entities for understanding the user's intent, and for searching a knowledge database for documents responsive to the query. When additional information is needed for determining more relevant results, a conversation strategy is determined, and a question is formulated for generating a conversation with the user for clarifying the user's intent, confirming a solution, or obtaining additional information. The user is enabled to provide a follow-up response that is related to a previously identified entity. The entity is edited in the query, and responses are refined responsive to the edited query.

Conversational virtual assistant

The subject disclosure is directed towards using primary data deduplication concepts for more efficient access of data via content addressable caches. Chunks of data, such as deduplicated data chunks, are maintained in a fast access client-side cache, such as containing chunks based upon access patterns. The chunked content is content addressable via a hash or other unique identifier of that content in the system. When a chunk is needed, the client-side cache (or caches) is checked for the chunk before going to a file server for the chunk. The file server may likewise maintain content addressable (chunk) caches. Also described are cache maintenance, management and organization, including pre-populating caches with chunks, as well as using RAM and/or solid-state storage device caches.

Growing community of inventors

Sammamish, WA, United States of America

Chenguang Zhu