-
公开(公告)号：US20210390269A1
公开(公告)日：2021-12-16
申请号：US16900481
申请日：2020-06-12
摘要： A method and machine translation system for bi-directional translation of textual sequences between a first language and a second language are described. The machine translation system includes a first autoencoder configured to receive a vector representation of a first textual sequence in the first language and encode the vector representation of the first textual sequence into a first sentence embedding. The machine translation system also includes a sum-product network (SPN) configured to receive the first sentence embedding and generate a second sentence embedding by maximizing a first conditional probability of the second sentence embedding given the first sentence embedding and a second autoencoder receiving the second sentence embedding, the second autoencoder being trained to decode the second sentence embedding into a vector representation of a second textual sequence in the second language.
-
公开(公告)号：US11003995B2
公开(公告)日：2021-05-11
申请号：US15789518
申请日：2017-10-20
申请人： Mehdi Rezagholizadeh , Md Akmal Haidar , Dalei Wu
发明人： Mehdi Rezagholizadeh , Md Akmal Haidar , Dalei Wu
摘要： Method and system for performing semi-supervised regression with a generative adversarial network (GAN) that includes a generator comprising a first neural network and a discriminator comprising a second neural network, comprising: outputting, from the first neural network, generated samples derived from a random noise vector; inputting, to the second neural network, the generated samples, a plurality of labelled training samples, and a plurality of unlabelled training samples; and outputting, from the second neural network, a predicted continuous label for each of a plurality of the generated samples and unlabelled samples.
-
公开(公告)号：US11586833B2
公开(公告)日：2023-02-21
申请号：US16900481
申请日：2020-06-12
摘要： A method and machine translation system for bi-directional translation of textual sequences between a first language and a second language are described. The machine translation system includes a first autoencoder configured to receive a vector representation of a first textual sequence in the first language and encode the vector representation of the first textual sequence into a first sentence embedding. The machine translation system also includes a sum-product network (SPN) configured to receive the first sentence embedding and generate a second sentence embedding by maximizing a first conditional probability of the second sentence embedding given the first sentence embedding and a second autoencoder receiving the second sentence embedding, the second autoencoder being trained to decode the second sentence embedding into a vector representation of a second textual sequence in the second language.
-
公开(公告)号：US20220122590A1
公开(公告)日：2022-04-21
申请号：US17076794
申请日：2020-10-21
申请人： Md Akmal HAIDAR , Chao XING
发明人： Md Akmal HAIDAR , Chao XING
摘要： Computer implemented method and system for automatic speech recognition. A first speech sequence is processed, using a time reduction operation of an encoder NN, into a second speech sequence that comprises a second set of speech frame feature vectors that each concatenate information from a respective plurality of speech frame feature vectors included in the first set, wherein the second speech sequence includes fewer speech frame feature vectors than the first speech sequence. The second speech sequence is transformed, using a self-attention operation of the encoder NN, into a third speech sequence that comprises a third set of speech frame feature vectors. The third speech sequence is processed, using a probability operation of the encoder NN, to predict a sequence of first labels corresponding to the third set of speech frame feature vectors. The third speech sequence is also processed using a decoder NN to predict a sequence of second labels corresponding to the third set of speech frame feature vectors.
-
公开(公告)号：US11151334B2
公开(公告)日：2021-10-19
申请号：US16143128
申请日：2018-09-26
摘要： In at least one broad aspect, described herein are systems and methods in which a latent representation shared between two languages is built and/or accessed, and then leveraged for the purpose of text generation in both languages. Neural text generation techniques are applied to facilitate text generation, and in particular the generation of sentences (i.e., sequences of words or subwords) in both languages, in at least some embodiments.
-
6.发明申请公开(公告)号：US20190122120A1
公开(公告)日：2019-04-25
申请号：US15789628
申请日：2017-10-20
申请人： Dalei Wu , Md Akmal Haidar , Mehdi Rezagholizadeh , Alan Do-Omri
发明人： Dalei Wu , Md Akmal Haidar , Mehdi Rezagholizadeh , Alan Do-Omri
摘要： A method and system for augmenting a training dataset for a generative adversarial network (GAN). The training dataset includes labelled data samples and unlabelled data samples. The method includes: receiving generated samples generated using a first neural network of the GAN and the unlabelled samples of training dataset; determining a decision value for a sample from a decision function, wherein the sample is a generated sample of the generated samples or an unlabelled sample of the unlabelled samples of the training dataset; comparing the decision value to a threshold; in response to determining that the decision value exceeds the threshold: predicting a label for a sample; assigning the label to the sample; and augmenting the training dataset to include the sample with the assigned label as a labelled sample.
-
7.发明申请公开(公告)号：US20220335303A1
公开(公告)日：2022-10-20
申请号：US17233323
申请日：2021-04-16
摘要： Methods, devices and processor-readable media for knowledge distillation using intermediate representations are described. A student model is trained using a Dropout-KD approach in which intermediate layer selection is performed efficiently such that the skip, search, and overfitting problems in intermediate layer KD may be solved. Teacher intermediate layers are selected randomly at each training epoch, with the layer order preserved to avoid breaking information flow. Over the course of multiple training epochs, all of the teacher intermediate layers are used for knowledge distillation. A min-max data augmentation method is also described based on the intermediate layer selection of the Dropout-KD training method.
-
8.发明授权公开(公告)号：US11120337B2
公开(公告)日：2021-09-14
申请号：US15789628
申请日：2017-10-20
申请人： Dalei Wu , Md Akmal Haidar , Mehdi Rezagholizadeh , Alan Do-Omri
发明人： Dalei Wu , Md Akmal Haidar , Mehdi Rezagholizadeh , Alan Do-Omri
摘要： A method and system for augmenting a training dataset for a generative adversarial network (GAN). The training dataset includes labelled data samples and unlabelled data samples. The method includes: receiving generated samples generated using a first neural network of the GAN and the unlabelled samples of training dataset; determining a decision value for a sample from a decision function, wherein the sample is a generated sample of the generated samples or an unlabelled sample of the unlabelled samples of the training dataset; comparing the decision value to a threshold; in response to determining that the decision value exceeds the threshold: predicting a label for a sample; assigning the label to the sample; and augmenting the training dataset to include the sample with the assigned label as a labelled sample.
-
公开(公告)号：US20200097554A1
公开(公告)日：2020-03-26
申请号：US16143128
申请日：2018-09-26
摘要： In at least one broad aspect, described herein are systems and methods in which a latent representation shared between two languages is built and/or accessed, and then leveraged for the purpose of text generation in both languages. Neural text generation techniques are applied to facilitate text generation, and in particular the generation of sentences (i.e., sequences of words or subwords) in both languages, in at least some embodiments.
-
10.发明授权公开(公告)号：US11715461B2
公开(公告)日：2023-08-01
申请号：US17076794
申请日：2020-10-21
申请人： Md Akmal Haidar , Chao Xing
发明人： Md Akmal Haidar , Chao Xing
CPC分类号： G10L15/16 , G10L15/063
摘要： Computer implemented method and system for automatic speech recognition. A first speech sequence is processed, using a time reduction operation of an encoder NN, into a second speech sequence comprising a second set of speech frame feature vectors that each concatenate information from a respective plurality of speech frame feature vectors included in the first set and includes fewer speech frame feature vectors than the first speech sequence. The second speech sequence is transformed, using a self-attention operation of the encoder NN, into a third speech sequence comprising a third set of speech frame feature vectors. The third speech sequence is processed using a probability operation of the encoder NN, to predict a sequence of first labels corresponding to the third set of speech frame feature vectors, and using a decoder NN to predict a sequence of second labels corresponding to the third set of speech frame feature vectors.
-
-
-
-
-
-
-
-
-
搜索结果
11 条记录 (耗时 0.016 秒)
