Salesforce Com, Inc.

Salesforce, Inc.

James Bradbury

Richard Socher

Caiming Xiong

Bryan McCann

Kazuma Hashimoto

Stephen Merity

Alexander Rosenberg Johansen

Raffaella Buschiazzo

Teresa Anna Marshall

Stephen Joseph Merity

Bryan Mccann

The technology disclosed proposes using a combination of computationally cheap, less-accurate bag of words (BoW) model and computationally expensive, more-accurate long short-term memory (LSTM) model to perform natural processing tasks such as sentiment analysis. The use of cheap, less-accurate BoW model is referred to herein as 'skimming'. The use of expensive, more-accurate LSTM model is referred to herein as “reading”. The technology disclosed presents a probability-based guider (PBG). PBG combines the use of BoW model and the LSTM model. PBG uses a probability thresholding strategy to determine, based on the results of the BoW model, whether to invoke the LSTM model for reliably classifying a sentence as positive or negative. The technology disclosed also presents a deep neural network-based decision network (DDN) that is trained to learn the relationship between the BoW model and the LSTM model and to invoke only one of the two models.

Deep neural network-based decision network

The technology disclosed provides a quasi-recurrent neural network (QRNN) encoder-decoder model that alternates convolutional layers, which apply in parallel across timesteps, and minimalist recurrent pooling layers that apply in parallel across feature dimensions.

Quasi-recurrent neural network based encoder-decoder model

A system automatically generates recurrent neural network (RNN) architectures for performing specific tasks, for example, machine translation. The system represents RNN architectures using a domain specific language (DSL). The system generates candidate RNN architectures. The system predicts performances of the generated candidate RNN architectures, for example, using a neural network. The system filters the candidate RNN architectures based on their predicted performance. The system generates code for selected a candidate architectures. The generated code represents an RNN that is configured to perform the specific task. The system executes the generated code, for example, to evaluate an RNN or to use the RNN in an application.

Domain specific language for generation of recurrent neural network architectures

Approaches for the translation of structured text include an embedding module for encoding and embedding source text in a first language, an encoder for encoding output of the embedding module, a decoder for iteratively decoding output of the encoder based on generated tokens in translated text from previous iterations, a beam module for constraining output of the decoder with respect to possible embedded tags to include in the translated text for a current iteration using a beam search, and a layer for selecting a token to be included in the translated text for the current iteration. The translated text is in a second language different from the first language. In some embodiments, the approach further includes scoring and pointer modules for selecting the token based on the output of the beam module or copied from the source text or reference text from a training pair best matching the source text.

Systems and methods for structured text translation with tag alignment

The technology disclosed provides a so-called 'pointer sentinel mixture architecture' for neural network sequence models that has the ability to either reproduce a token from a recent context or produce a token from a predefined vocabulary. In one implementation, a pointer sentinel-LSTM architecture achieves state of the art language modeling performance of 70.9 perplexity on the Penn Treebank dataset, while using far fewer parameters than a standard softmax LSTM.

Pointer sentinel mixture architecture

Structured text translation

An attentional neural machine translation model is provided for the task of machine translation that, according to some embodiments, leverages the hierarchical structure of language to perform natural language processing without a priori annotation. Other features are also provided.

Neural machine translation with latent tree attention

The technology disclosed proposes using a combination of computationally cheap, less-accurate bag of words (BoW) model and computationally expensive, more-accurate long short-term memory (LSTM) model to perform natural processing tasks such as sentiment analysis. The use of cheap, less-accurate BoW model is referred to herein as 'skimming'. The use of expensive, more-accurate LSTM model is referred to herein as 'reading'. The technology disclosed presents a probability-based guider (PBG). PBG combines the use of BoW model and the LSTM model. PBG uses a probability thresholding strategy to determine, based on the results of the BoW model, whether to invoke the LSTM model for reliably classifying a sentence as positive or negative. The technology disclosed also presents a deep neural network-based decision network (DDN) that is trained to learn the relationship between the BoW model and the LSTM model and to invoke only one of the two models.

Probability-based guider

We introduce an attentional neural machine translation model for the task of machine translation that accomplishes the longstanding goal of natural language processing to take advantage of the hierarchical structure of language without a priori annotation. The model comprises a recurrent neural network grammar (RNNG) encoder with a novel attentional RNNG decoder and applies policy gradient reinforcement learning to induce unsupervised tree structures on both the source sequence and target sequence. When trained on character-level datasets with no explicit segmentation or parse annotation, the model learns a plausible segmentation and shallow parse, obtaining performance close to an attentional baseline.

Growing community of inventors

San Francisco, CA, United States of America

James Bradbury