知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

31 records (took 0.018 seconds)

    Teaching syntax by adversarial distraction
    11.
    发明授权
    Teaching syntax by adversarial distraction 有权

    公开(公告)号：US11194974B2

    公开(公告)日：2021-12-07

    申请号：US16522742

    申请日：2019-07-26

    Applicant: NEC Laboratories America, Inc.

    Inventor： Christopher Malon ,  Asim Kadav ,  Juho Kim

    IPC: G10L15/00 ,  G10L15/28 ,  G06F17/00 ,  G06F40/40 ,  G06N3/08

    Abstract: A computer-implemented method and system are provided for teaching syntax for training a neural network based natural language inference model. The method includes selectively performing, by the hardware processor, person reversal on a set of hypothesis sentences, based on person reversal prevention criteria, to obtain a first training data set. The method further includes enhancing, by the hardware processor, a robustness of the neural network based natural language inference model to syntax changes by training the neural network based natural language inference model on original training data combined with the first data set.

    CONTROLLED TEXT GENERATION WITH SUPERVISED REPRESENTATION DISENTANGLEMENT AND MUTUAL INFORMATION MINIMIZATION
    13.
    发明申请
    CONTROLLED TEXT GENERATION WITH SUPERVISED REPRESENTATION DISENTANGLEMENT AND MUTUAL INFORMATION MINIMIZATION 有权

    公开(公告)号：US20210174213A1

    公开(公告)日：2021-06-10

    申请号：US17115464

    申请日：2020-12-08

    Applicant: NEC Laboratories America, Inc.

    Inventor： Renqiang Min ,  Christopher Malon ,  Pengyu Cheng

    IPC: G06N3/08 ,  G06F40/20

    Abstract: A computer-implemented method is provided for disentangled data generation. The method includes accessing, by a bidirectional Long Short-Term Memory (LSTM) with a multi-head attention mechanism, a dataset including a plurality of pairs each formed from a given one of a plurality of input text structures and given one of a plurality of style labels for the plurality of input text structures. The method further includes training the bidirectional LSTM as an encoder to disentangle a sequential text input into disentangled representations comprising a content embedding and a style embedding based on a subset of the dataset. The method also includes training a unidirectional LSTM as a decoder to generate a next text structure prediction for the sequential text input based on previously generated text structure information and a current word, from a disentangled representation with the content embedding and the style embedding.

    Semantic Representations of Rare Words in a Neural Probabilistic Language Model
    14.
    发明申请
    Semantic Representations of Rare Words in a Neural Probabilistic Language Model 审中-公开
    神话概率语言模型中罕见词的语义表示

    公开(公告)号：US20140236577A1

    公开(公告)日：2014-08-21

    申请号：US14166228

    申请日：2014-01-28

    Applicant: NEC Laboratories America, Inc.

    Inventor： Christopher Malon ,  Bing Bai

    IPC: G06F17/28 ,  G06N3/02

    CPC classification number: G06F17/28 ,  G06F17/2785 ,  G06N3/02

    Abstract: Systems and methods are disclosed for representing a word by extracting n-dimensions for the word from an original language model; if the word has been previously processed, use values previously chosen to define an (n+m) dimensional vector and otherwise randomly selecting m values to define the (n+m) dimensional vector; and applying the (n+m) dimensional vector to represent words that are not well-represented in the language model.

    Abstract translation: 公开了通过从原始语言模型中提取单词的n维来表示单词的系统和方法; 如果字已经被处理过，则使用先前选择的值来定义（n + m）维向量，否则随机选择m个值来定义（n + m）维向量; 以及应用（n + m）维向量来表示在语言模型中未被很好表示的单词。

    VERIFYING COMPLEX SENTENCES WITH ARTIFICIAL INTELLIGENCE
    16.
    发明申请
    VERIFYING COMPLEX SENTENCES WITH ARTIFICIAL INTELLIGENCE 有权

    公开(公告)号：US20250103812A1

    公开(公告)日：2025-03-27

    申请号：US18888763

    申请日：2024-09-18

    Applicant: NEC Laboratories America, Inc.

    Inventor： Christopher Malon

    IPC: G06F40/289 ,  G06F40/40 ,  G06N3/08 ,  G06N5/045 ,  G16H15/00

    Abstract: Systems and methods for verifying complex sentences with artificial intelligence. Claim sentences can be filtered with source texts using a confirmation threshold, an unsupported threshold, and entailment probabilities computed by a natural language inference (NLI) classifier to obtain initial verification pairs. A trained imagination model can generate entailment outputs by employing initial verification pairs. A trained generalization model can generate generalized outputs by generalizing entailment outputs. Missing evidence generalizations can be chosen from sampled generalized outputs based on overlaps between sampled generalized outputs The NLI classifier can compute a final verification decision of the source texts against the missing evidence generalizations to obtain verified claim sentences. A corrective action for a monitored entity can be performed using the verified claim sentences.

    LANGUAGE MODELS WITH DYNAMIC OUTPUTS
    17.
    发明申请
    LANGUAGE MODELS WITH DYNAMIC OUTPUTS 有权

    公开(公告)号：US20250053774A1

    公开(公告)日：2025-02-13

    申请号：US18776926

    申请日：2024-07-18

    Applicant: NEC Laboratories America, Inc.

    Inventor： Christopher Malon ,  Christopher A White ,  Renqiang Min ,  Iain Melvin

    IPC: G06N3/006 ,  G06N3/092 ,  G06N5/04 ,  G16H50/70

    Abstract: Methods and systems for answering a query include generating first tokens in response to an input query using a language model, the first tokens including a retrieval rule. A retrieval rule is used to search for information to generate dynamic tokens. The retrieval rule in the first tokens is replaced with the dynamic tokens to generate a dynamic partial response. Second tokens are generated in response to the input query. The second tokens are appended to the dynamic partial response to generate an output responsive to the input query.

    Enhanced word embedding
    18.
    发明授权
    Enhanced word embedding 有权

    公开(公告)号：US12205026B2

    公开(公告)日：2025-01-21

    申请号：US17674461

    申请日：2022-02-17

    Applicant: NEC Laboratories America, Inc.

    Inventor： Christopher Malon

    IPC: G06N3/08 ,  G06F40/166 ,  G06F40/242 ,  G06F40/279

    Abstract: Methods and systems for language processing include augmenting an original training dataset to produce an augmented dataset that includes a first example that includes a first scrambled replacement for a first word and a definition of the first word, and a second example that includes a second scrambled replacement for the first word and a definition of an alternative to the first word. A neural network classifier is trained using the augmented dataset.

    SUMMARIZING PREVALENT OPINIONS FOR MEDICAL DECISION-MAKING
    19.
    发明公开
    SUMMARIZING PREVALENT OPINIONS FOR MEDICAL DECISION-MAKING 审中-公开

    公开(公告)号：US20240274251A1

    公开(公告)日：2024-08-15

    申请号：US18439274

    申请日：2024-02-12

    Applicant: NEC Laboratories America, Inc.

    Inventor： Christopher Malon

    IPC: G16H20/00 ,  G06F40/205 ,  G06F40/40

    CPC classification number: G16H20/00 ,  G06F40/205 ,  G06F40/40

    Abstract: Methods and systems for document summarization include splitting documents into sentences and sorting the sentences by a metric that promotes review opinion prevalence from the documents to generate a ranked list of sentences. Groups of sentences with similar embeddings are formed and a trained generalization encoder-decoder model is applied to output a common generalization of the sentences in each group. Sentences are added to a summary from the generalizations corresponding to the sentences in the ranked list, in rank-order, until a target summary length has been reached. An action is performed responsive to the summary.

Patent Agency Ranking