公开(公告)号：US20220067284A1

公开(公告)日：2022-03-03

申请号：US17125468

申请日：2020-12-17

Applicant: salesforce.com, inc.

Inventor： Junxian He ,  Wojciech Kryscinski ,  Bryan McCann

IPC: G06F40/284 ,  G06N7/00

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：US10909157B2

公开(公告)日：2021-02-02

申请号：US16051188

申请日：2018-07-31

Applicant: salesforce.com, inc.

Inventor： Romain Paulus ,  Wojciech Kryscinski ,  Caiming Xiong

IPC: G06F40/211 ,  G06F40/30 ,  G06F16/00 ,  G06N20/00 ,  G06F16/34 ,  G06K9/62 ,  G06N3/04 ,  G06F16/33

Abstract: A system is disclosed for providing an abstractive summary of a source textual document. The system includes an encoder, a decoder, and a fusion layer. The encoder is capable of generating an encoding for the source textual document. The decoder is separated into a contextual model and a language model. The contextual model is capable of extracting words from the source textual document using the encoding. The language model is capable of generating vectors paraphrasing the source textual document based on pre-training with a training dataset. The fusion layer is capable of generating the abstractive summary of the source textual document from the extracted words and the generated vectors for paraphrasing. In some embodiments, the system utilizes a novelty metric to encourage the generation of novel phrases for inclusion in the abstractive summary.