Invention Grant
- Patent Title: Abstraction of text summarization
-
Application No.: US16051188Application Date: 2018-07-31
-
Publication No.: US10909157B2Publication Date: 2021-02-02
- Inventor: Romain Paulus , Wojciech Kryscinski , Caiming Xiong
- Applicant: salesforce.com, inc.
- Applicant Address: US CA San Francisco
- Assignee: salesforce.com, inc.
- Current Assignee: salesforce.com, inc.
- Current Assignee Address: US CA San Francisco
- Agency: Haynes and Boone, LLP
- Main IPC: G06F40/211
- 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.
Information query