公开(公告)号：US20240203532A1

公开(公告)日：2024-06-20

申请号：US18589215

申请日：2024-02-27

Applicant: Salesforce, Inc.

Inventor： Ali Madani ,  Bryan McCann ,  Nikhil Naik

IPC: G16B40/30 ,  G06F30/20 ,  G06F111/08 ,  G16B5/20 ,  G16B15/20 ,  G16B25/10 ,  G16B30/00 ,  G16B40/20 ,  G16B50/10

CPC classification number: G16B40/30 ,  G06F30/20 ,  G16B5/20 ,  G16B15/20 ,  G16B25/10 ,  G16B30/00 ,  G16B40/20 ,  G16B50/10 ,  G06F2111/08

Abstract: The present disclosure provides systems and methods for controllable protein generation. According to some embodiments, the systems and methods leverage neural network models and techniques that have been developed for other fields, in particular, natural language processing (NLP). In some embodiments, the systems and methods use or employ models implemented with transformer architectures developed for language modeling and apply the same to generative modeling for protein engineering.

公开(公告)号：US11934781B2

公开(公告)日：2024-03-19

申请号：US17125468

申请日：2020-12-17

Applicant: Salesforce, Inc.

Inventor： Junxian He ,  Wojciech Kryscinski ,  Bryan McCann

IPC: G06F40/10 ,  G06F40/143 ,  G06F40/169 ,  G06F40/284 ,  G06N7/01 ,  G06F3/0483

CPC classification number: G06F40/284 ,  G06N7/01 ,  G06F3/0483

Abstract: Embodiments described herein provide a flexible controllable summarization system that allows users to control the generation of summaries without manually editing or writing the summary, e.g., without the user actually adding or deleting certain information under various granularity. Specifically, the summarization system performs controllable summarization through keywords manipulation. A neural network model is learned to generate summaries conditioned on both the keywords and source document so that at test time a user can interact with the neural network model through a keyword interface, potentially enabling multi-factor control.

公开(公告)号：US11948665B2

公开(公告)日：2024-04-02

申请号：US17001068

申请日：2020-08-24

Applicant: Salesforce, Inc.

Inventor： Ali Madani ,  Bryan McCann ,  Nikhil Naik

IPC: G16B40/30 ,  G06F30/20 ,  G06F111/08 ,  G16B5/20 ,  G16B15/20 ,  G16B25/10 ,  G16B30/00 ,  G16B40/20 ,  G16B50/10

CPC classification number: G16B40/30 ,  G06F30/20 ,  G16B5/20 ,  G16B15/20 ,  G16B25/10 ,  G16B30/00 ,  G16B40/20 ,  G16B50/10 ,  G06F2111/08

Abstract: The present disclosure provides systems and methods for controllable protein generation. According to some embodiments, the systems and methods leverage neural network models and techniques that have been developed for other fields, in particular, natural language processing (NLP). In some embodiments, the systems and methods use or employ models implemented with transformer architectures developed for language modeling and apply the same to generative modeling for protein engineering.

公开(公告)号：US11934952B2

公开(公告)日：2024-03-19

申请号：US17124317

申请日：2020-12-16

Applicant: Salesforce, Inc.

Inventor： Tianxing He ,  Ehsan Hosseini-Asl ,  Bryan McCann ,  Caiming Xiong

IPC: G06N3/08

CPC classification number: G06N3/08

Abstract: Embodiments described herein provide natural language processing (NLP) systems and methods that utilize energy-based models (EBMs) to compute an exponentially-weighted energy-like term in the loss function to train an NLP classifier. Specifically, noise contrastive estimation (NCE) procedures are applied together with the EBM-based loss objectives for training the NLPs.