公开(公告)号：US20210374553A1

公开(公告)日：2021-12-02

申请号：US17015858

申请日：2020-09-09

Applicant: salesforce.com, inc.

Inventor： Junnan Li ,  Chu Hong Hoi

IPC: G06N3/08 ,  G06N3/04

Abstract: Embodiments described herein provide systems and methods for noise-robust contrastive learning. In view of the need for a noise-robust learning system, embodiments described herein provides a contrastive learning mechanism that combats noise by learning robust representations of the noisy data samples. Specifically, the training images are projected into a low-dimensional subspace, and the geometric structure of the subspace is regularized with: (1) a consistency contrastive loss that enforces images with perturbations to have similar embeddings; and (2) a prototypical contrastive loss augmented with a predetermined learning principle, which encourages the embedding for a linearly-interpolated input to have the same linear relationship with respect to the class prototypes. The low-dimensional embeddings are also trained to reconstruct the high-dimensional features, which preserves the learned information and regularizes the classifier.

公开(公告)号：US20210374132A1

公开(公告)日：2021-12-02

申请号：US17093885

申请日：2020-11-10

Applicant: salesforce.com, inc.

Inventor： Wenzhuo Yang ,  Jia Li ,  Chenxi Li ,  Latrice Barnett ,  Markus Anderle ,  Simo Arajarvi ,  Harshavardhan Utharavalli ,  Caiming Xiong ,  Richard Socher ,  Chu Hong Hoi

IPC: G06F16/2457 ,  G06N20/20

Abstract: Embodiments are directed to a machine learning recommendation system. The system receives a user query for generating a recommendation for one or more items with an explanation associated with recommending the one or more items. The system obtains first features of at least one user and second features of a set of items. The system provides the first features and the second features to a first machine learning network for determining a predicted score for an item. The system provides a portion of the first features and a portion of the second features to second machine learning networks for determining explainability scores for an item and generating corresponding explanation narratives. The system provides the recommendation for one or more items and corresponding explanation narratives based on ranking predicted scores and explainability scores for the items.

公开(公告)号：US20210174798A1

公开(公告)日：2021-06-10

申请号：US16870571

申请日：2020-05-08

Applicant: salesforce.com, inc.

Inventor： Chien-Sheng Wu ,  Chu Hong Hoi ,  Caiming Xiong

IPC: G10L15/22 ,  G06K9/62 ,  G10L15/30 ,  G10L15/16

Abstract: Embodiments described in this disclosure illustrate the use of self-/semi supervised approaches for label-efficient DST in task-oriented dialogue systems. Conversational behavior is modeled by next response generation and turn utterance generation tasks. Prediction consistency is strengthened by augmenting data with stochastic word dropout and label guessing. Experimental results show that by exploiting self-supervision the joint goal accuracy can be boosted with limited labeled data.

公开(公告)号：US20210173829A1

公开(公告)日：2021-06-10

申请号：US16866034

申请日：2020-05-04

Applicant: salesforce.com, inc.

Inventor： Jichuan Zeng ,  Xi Lin ,  Chu Hong Hoi

IPC: G06F16/242 ,  G06F40/284 ,  G06F40/47 ,  G06F16/2452

Abstract: A system and method for translating questions into database queries are provided. A text to database query system receives a natural language question and a structure in a database. Question tokens are generated from the question and query tokens are generated from the structure in the database. The question tokens and query tokens are concatenated into a sentence and a sentence token is added to the sentence. A BERT network generates question hidden states for the question tokens, query hidden states for the query tokens, and a classifier hidden state for the sentence token. A translatability predictor network determines if the question is translatable or untranslatable. A decoder converts a translatable question into an executable query. A confusion span predictor network identifies a confusion span in the untranslatable question that causes the question to be untranslatable. An auto-correction module to auto-correct the tokens in the confusion span.

公开(公告)号：US20210049236A1

公开(公告)日：2021-02-18

申请号：US16581035

申请日：2019-09-24

Applicant: salesforce.com, inc.

Inventor： Xuan Phi Nguyen ,  Shafiq Rayhan Joty ,  Chu Hong Hoi

IPC: G06F17/27

Abstract: Embodiments described herein provide an attention-based tree encoding mechanism. Specifically, the attention layer receives as input the pre-parsed constituency tree of a sentence and the lower-layer representations of all nodes. The attention layer then performs upward accumulation to encode the tree structure from leaves to the root in a bottom-up fashion. Afterwards, weighted aggregation is used to compute the final representations of non-terminal nodes.