-
公开(公告)号：US12260185B2
公开(公告)日：2025-03-25
申请号：US17159625
申请日：2021-01-27
Applicant: Salesforce, Inc.
Inventor： Chien-Sheng Wu , Wenhao Liu , Caiming Xiong , Linqing Liu
IPC: G06F40/56 , G06F40/205
Abstract: Dialogue summarization is challenging due to its multi-speaker standpoints, casual spoken language style, and limited labelled data. The embodiments are directed to a coarse-to-fine dialogue summarization model that improves abstractive dialogue summarization quality and enables granular controllability. A summary draft that includes key words for turns in a dialogue conversation history is created. The summary draft includes pseudo-labelled interrogative pronoun categories and noisy key phrases. The dialogue conversation history is divided into segments. A generate language model is trained to generate a segment summary for each dialogue segment using a portion of the summary draft that corresponds to at least one dialogue turn in the dialogue segment. A dialogue summary is generated using the generative language model trained using the summary draft.
-
公开(公告)号：US11941356B2
公开(公告)日：2024-03-26
申请号：US17080478
申请日：2020-10-26
Applicant: Salesforce, Inc.
Inventor： Linqing Liu , Caiming Xiong
Abstract: Embodiments described herein propose a densely connected Transformer architecture in which each Transformer layer takes advantages of all previous layers. Specifically, the input for each Transformer layer comes from the outputs of all its preceding layers; and the output information of each layer will be incorporated in all its subsequent layers. In this way, a L-layer Transformer network will have L(L+1)/2 connections. In this way, the dense connection allows the linguistic information learned by the lower layer to be directly propagated to all upper layers and encourages feature reuse throughout the network. Each layer is thus directly optimized from the loss function in the fashion of implicit deep supervision.
-
Search Results
2
records
(took 0.009 seconds)
