公开(公告)号：US11600194B2

公开(公告)日：2023-03-07

申请号：US16006691

申请日：2018-06-12

Applicant: salesforce.com, inc.

Inventor： Bryan McCann ,  Nitish Shirish Keskar ,  Caiming Xiong ,  Richard Socher

IPC: G09B7/02 ,  G06F16/9032 ,  G06F40/30 ,  G06F40/284 ,  G06N3/084 ,  G06F40/35 ,  G06N3/082 ,  G06N5/04 ,  G06N3/04 ,  G06F16/34 ,  G06F40/216

Abstract: Approaches for natural language processing include a multi-layer encoder for encoding words from a context and words from a question in parallel, a multi-layer decoder for decoding the encoded context and the encoded question, a pointer generator for generating distributions over the words from the context, the words from the question, and words in a vocabulary based on an output from the decoder, and a switch. The switch generates a weighting of the distributions over the words from the context, the words from the question, and the words in the vocabulary, generates a composite distribution based on the weighting of the distribution over the first words from the context, the distribution over the second words from the question, and the distribution over the words in the vocabulary, and selects words for inclusion in an answer using the composite distribution.

公开(公告)号：US20230042327A1

公开(公告)日：2023-02-09

申请号：US17579377

申请日：2022-01-19

Applicant: salesforce.com, inc.

Inventor： Zhiwei Liu ,  Caiming Xiong ,  Jia Li ,  Yongjun Chen

IPC: G06N3/08 ,  G06N3/04

Abstract: A method for providing a neural network system includes performing contrastive learning to the neural network system to generate a trained neural network system. The performing the contrastive learning includes performing first model augmentation to a first encoder of the neural network system to generate a first embedding of a sample, performing second model augmentation to the first encoder to generate a second embedding of the sample, and optimizing the first encoder using a contrastive loss based on the first embedding and the second embedding. The trained neural network system is provided to perform a task.

公开(公告)号：US11562287B2

公开(公告)日：2023-01-24

申请号：US15885727

申请日：2018-01-31

Applicant: salesforce.com, inc.

Inventor： Caiming Xiong ,  Tianmin Shu ,  Richard Socher

IPC: G06N20/00 ,  G06N3/08 ,  G06F9/48 ,  G06N3/04

Abstract: The disclosed technology reveals a hierarchical policy network, for use by a software agent, to accomplish an objective that requires execution of multiple tasks. A terminal policy learned by training the agent on a terminal task set, serves as a base task set of the intermediate task set. An intermediate policy learned by training the agent on an intermediate task set serves as a base policy of the top policy. A top policy learned by training the agent on a top task set serves as a base task set of the top task set. The agent is configurable to accomplish the objective by traversal of the hierarchical policy network. A current task in a current task set is executed by executing a previously-learned task selected from a corresponding base task set governed by a corresponding base policy, or performing a primitive action selected from a library of primitive actions.

公开(公告)号：US20220374459A1

公开(公告)日：2022-11-24

申请号：US17533613

申请日：2021-11-23

Applicant: salesforce.com, inc.

Inventor： Ye Liu ,  Kazuma Hashimoto ,  Yingbo Zhou ,  Semih Yavuz ,  Caiming Xiong

IPC: G06F16/335 ,  G06F16/332 ,  G06F16/31

Abstract: Embodiments described herein provide a dense hierarchical retrieval for open-domain question and answering for a corpus of documents using a document-level and passage-level dense retrieval model. Specifically, each document is viewed as a structural collection that has sections, subsections and paragraphs. Each document may be split into short length passages, where a document-level retrieval model and a passage-level retrieval model may be applied to return a smaller set of filtered texts. Top documents may be identified after encoding the question and the documents and determining document relevance scores to the encoded question. Thereafter, a set of top passages are further identified based on encoding of the passages and determining passage relevance scores to the encoded question. The document and passage relevance scores may be used in combination to determine a final retrieval ranking for the documents having the set of top passages.

公开(公告)号：US11495011B2

公开(公告)日：2022-11-08

申请号：US16988536

申请日：2020-08-07

Applicant: salesforce.com, inc.

Inventor： Shu Zhang ,  Chetan Ramaiah ,  Ran Xu ,  Caiming Xiong

IPC: G06K9/00 ,  G06V10/75 ,  G06K9/62 ,  G06V10/22 ,  G06V30/414 ,  G06V30/10

Abstract: The system has a form analysis module that receives an image of a form into which values have been filled for the possible fields of information on the form, such as first name, address, age, and the like. By using a library of form templates, a form analysis module allows both flexibility of form processing and simplicity for the user. That is, the techniques used by the form analysis module allow the processing of any form image for which the library has a form template example. The form image need not precisely match any form template, but rather may be scaled or shifted relative to a corresponding template. Additionally, the user need only provide the form image itself, without providing any additional exemplars, metadata for training, or the like.

公开(公告)号：US20220293094A1

公开(公告)日：2022-09-15

申请号：US17202077

申请日：2021-03-15

Applicant: salesforce.com, inc.

Inventor： Yixin Mao ,  Zachary Alexander ,  Victor Winslow Yee ,  Joseph R. Zeimen ,  Na Cheng ,  Chien-Sheng Wu ,  Wenhao Liu ,  Caiming Xiong

IPC: G10L15/16 ,  H04L12/58 ,  G10L15/22 ,  G10L15/08 ,  G10L15/06

Abstract: A system uses conversation engines to process natural language requests and conduct automatic conversations with users. The system generates responses to users in an online conversation. The system ranks generated user responses for the online conversation. The system generates a context vector based on a sequence of utterances of the conversation and generates response vectors for generated user responses. The system ranks the user responses based on a comparison of the context vectors and user response vectors. The system uses a machine learning based model that uses a pretrained neural network that supports multiple languages. The system determines a context of an utterance based on utterances in the conversation. The system generates responses and ranks them based on the context. The ranked responses are used to respond to the user.

公开(公告)号：US20220269946A1

公开(公告)日：2022-08-25

申请号：US17375728

申请日：2021-07-14

Applicant: salesforce.com, inc.

Inventor： Pan Zhou ,  Caiming Xiong ,  Chu Hong Hoi

IPC: G06N3/08 ,  G06N3/04

Abstract: Embodiments described herein provide a contrastive learning mechanism with self-labeling refinement, which iteratively employs the network and data themselves to generate more accurate and informative soft labels for contrastive learning. Specifically, the contrastive learning framework includes a self-labeling refinery module to explicitly generate accurate labels, and a momentum mix-up module to increase similarity between a query and its positive, which in turn implicitly improves label accuracy.

公开(公告)号：US11416688B2

公开(公告)日：2022-08-16

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 ,  G10L15/30 ,  G06F40/35 ,  G06N5/04 ,  G06N3/08 ,  G06K9/62 ,  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：US11328731B2

公开(公告)日：2022-05-10

申请号：US16903964

申请日：2020-06-17

Applicant: salesforce.com, inc.

Inventor： Weiran Wang ,  Yingbo Zhou ,  Caiming Xiong

IPC: G10L15/26

Abstract: System and methods for identifying a text word from a spoken utterance are provided. An ensemble BPE system that includes a phone BPE system and a character BPE system receives a spoken utterance. Both BPE systems include a multi-level language model (LM) and an acoustic model. The phone BPE system identifies first words from the spoken utterance and determine a first score for each first word. The first words are converted into character sequences. The character BPE model converts the character sequences into second words and determines a second score for each second word. For each word from the first words that matches a word in the second words the first and second scores are combined. The text word is the word with a highest score.

公开(公告)号：US20220139384A1

公开(公告)日：2022-05-05

申请号：US17088206

申请日：2020-11-03

Applicant: salesforce.com, inc.

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

IPC: G10L15/18 ,  G10L15/06

Abstract: Embodiments described herein provide methods and systems for training task-oriented dialogue (TOD) language models. In some embodiments, a TOD language model may receive a TOD dataset including a plurality of dialogues and a model input sequence may be generated from the dialogues using a first token prefixed to each user utterance and a second token prefixed to each system response of the dialogues. In some embodiments, the first token or the second token may be randomly replaced with a mask token to generate a masked training sequence and a masked language modeling (MLM) loss may be computed using the masked training sequence. In some embodiments, the TOD language model may be updated based on the MLM loss.