知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

11 records (took 0.014 seconds)

    SYSTEMS AND METHODS FOR FACTUAL EXTRACTION FROM LANGUAGE MODEL
    1.
    发明申请
    SYSTEMS AND METHODS FOR FACTUAL EXTRACTION FROM LANGUAGE MODEL 有权

    公开(公告)号：US20230083512A1

    公开(公告)日：2023-03-16

    申请号：US17588043

    申请日：2022-01-28

    Applicant: salesforce.com, inc.

    Inventor： Benjamin Newman ,  Nazneen Rajani ,  Prafulla Kumar Choubey

    IPC: G06F40/279 ,  G06F40/126 ,  G06N3/04

    Abstract: Embodiments described herein provide a system and method for extracting factual information. The system transforms a query into a natural language prompt in a format of a query subject and a queried relation. The system encodes, via an embedding layer of a pre-trained language model, the natural language prompt into a first embedding. The system encodes, via the adapter model, the first embedding into a second embedding based on a probability that the second embedding returns the factual information when the second embedding is fed the first attention layer of the pre-trained language model. The system decodes, by the first attention layer of the pre-trained language mode, the second embedding into a response to the query. The system extracts the factual information from the decoded response to the query.

    SYSTEMS AND METHODS FOR EXPLAINABLE AND FACTUAL MULTI-DOCUMENT SUMMARIZATION
    2.
    发明申请
    SYSTEMS AND METHODS FOR EXPLAINABLE AND FACTUAL MULTI-DOCUMENT SUMMARIZATION 有权

    公开(公告)号：US20230070497A1

    公开(公告)日：2023-03-09

    申请号：US17589675

    申请日：2022-01-31

    Applicant: salesforce.com, inc.

    Inventor： Jered McInerney ,  Wojciech Kryscinski ,  Nazneen Rajani

    IPC: G06F40/166 ,  G06F40/40 ,  G06F40/20 ,  G06N5/02

    Abstract: Embodiments described herein provide methods and systems for summarizing multiple documents. A system receives a plurality of documents and generates embeddings of the sentences from the plurality of documents. The embedded sentences are clustered in a representation space. Sentences from a reference summary are embedded and aligned with the closest cluster. Sentences from each cluster are summarized with the aligned reference sentences as a target. A loss is computed based on the summarized sentences and the aligned references, and the natural language processing model is updated based on the loss. Sentences may be masked from being used in the summarization by identifying sentences that are contradicted by other sentences within the plurality of documents.

    Leveraging language models for generating commonsense explanations
    4.
    发明授权
    Leveraging language models for generating commonsense explanations 有权

    公开(公告)号：US11366969B2

    公开(公告)日：2022-06-21

    申请号：US16393801

    申请日：2019-04-24

    Applicant: salesforce.com, inc.

    Inventor： Nazneen Rajani ,  Bryan McCann

    IPC: G06F40/30 ,  G06F40/284 ,  G06N5/02

    Abstract: According to some embodiments, systems and methods are provided to develop or provide common sense auto-generated explanations (CAGE) for the reasoning used by an artificial intelligence, neural network, or deep learning model to make a prediction. In some embodiments, the systems and methods use supervised fine-tuning on a language model (LM) to generate such explanations. These explanations may then be used for downstream classification.

    SYSTEMS AND METHODS FOR A K-NEAREST NEIGHBOR BASED MECHANISM OF NATURAL LANGUAGE PROCESSING MODELS
    5.
    发明申请
    SYSTEMS AND METHODS FOR A K-NEAREST NEIGHBOR BASED MECHANISM OF NATURAL LANGUAGE PROCESSING MODELS 有权

    公开(公告)号：US20210374488A1

    公开(公告)日：2021-12-02

    申请号：US17090553

    申请日：2020-11-05

    Applicant: salesforce.com, inc.

    Inventor： Nazneen Rajani ,  Tong Niu ,  Wenpeng Yin

    IPC: G06K9/62 ,  G06N3/08 ,  G06N3/063

    Abstract: Embodiments described herein adopts a k nearest neighbor (kNN) mechanism over a model's hidden representations to identify training examples closest to a given test example. Specifically, a training set of sequences and a test sequence are received, each of which is mapped to a respective hidden representation vector using a base model. A set of indices for each sequence index that minimizes a distance between the respective hidden state vector and a test hidden state vector is then determined A weighted k-nearest neighbor probability score can then be computed from the set of indices to generate a probability distribution over labels for the test sequence.

    SYSTEMS AND METHODS FOR ALIGNMENT-BASED PRE-TRAINING OF PROTEIN PREDICTION MODELS
    7.
    发明申请
    SYSTEMS AND METHODS FOR ALIGNMENT-BASED PRE-TRAINING OF PROTEIN PREDICTION MODELS 有权

    公开(公告)号：US20220122689A1

    公开(公告)日：2022-04-21

    申请号：US17153164

    申请日：2021-01-20

    Applicant: Salesforce.com, Inc.

    Inventor： Pascal Sturmfels ,  Ali Madani ,  Jesse Vig ,  Nazneen Rajani

    IPC: G16B5/20 ,  G16B30/10 ,  G16B40/20

    Abstract: Embodiments described herein provide an alignment-based pre-training mechanism for protein prediction. Specifically, the protein prediction model takes as input features derived from multiple sequence alignments (MSAs), which cluster proteins with related sequences. Features derived from MSAs, such as position specific scoring matrices and hidden Markov model (HMM) profiles, have long known to be useful features for predicting the structure of a protein. Thus, in order to predict profiles derived from MSAs from a single protein in the alignment, the neural network learns information about that protein's structure using HMM profiles derived from MSAs as labels during pre-training (rather than as input features in a downstream task).

    SYSTEM AND METHOD FOR NATURAL LANGUAGE PROCESSING USING NEURAL NETWORK
    8.
    发明申请
    SYSTEM AND METHOD FOR NATURAL LANGUAGE PROCESSING USING NEURAL NETWORK 有权

    公开(公告)号：US20210174204A1

    公开(公告)日：2021-06-10

    申请号：US17093478

    申请日：2020-11-09

    Applicant: salesforce.com, inc.

    Inventor： Wenpeng Yin ,  Nazneen Rajani ,  Richard Socher ,  Caiming Xiong

    IPC: G06N3/08 ,  G06F16/332 ,  G06F16/33 ,  G06F40/279 ,  G06F40/30

    Abstract: A method for using a neural network model for natural language processing (NLP) includes receiving training data associated with a source domain and a target domain; and generating one or more query batches. Each query batch includes one or more source tasks associated with the source domain and one or more target tasks associated with the target domain. For each query batch, class representations are generated for each class in the source domain and the target domain. A query batch loss for the query batch is generated based on the corresponding class representations. An optimization is performed on the neural network model by adjusting its network parameters based on the query batch loss. The optimized neural network model is used to perform one or more new NLP tasks.

Patent Agency Ranking