Deep reinforced model for abstractive summarization

R Paulus - US Patent 10,474,709, 2019‏ - Google Patents
Disclosed RNN-implemented methods and systems for abstractive text summarization
process input token embeddings of a document through an encoder that produces encoder …

Deep neural network-based decision network

AR Johansen, B McCann, J Bradbury… - US Patent …, 2022‏ - Google Patents
The technology disclosed proposes using a combination of computationally cheap, less-
accurate bag of words (BoW) model and computationally expensive, more-accurate long …

Neural machine translation with latent tree attention

J Bradbury - US Patent 10,565,318, 2020‏ - Google Patents
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 …

Memory grounded conversational reasoning and question answering for assistant systems

S Moon, PP Shah, A Kumar, R Subba - US Patent 11,657,094, 2023‏ - Google Patents
Natural-language Understanding, https://en. wikipedia. org/wiki/Natural-language
understanding, Feb. 15, 2018. Conversational AI and the Road Ahead, https://techcrunch …

Sentinel gate for modulating auxiliary information in a long short-term memory (lstm) neural network

LU Jiasen, C **ong, R Socher - US Patent 10,565,306, 2020‏ - Google Patents
The technology disclosed presents a novel spatial attention model that uses current hidden
state information of a decoder long short-term memory (LSTM) to guide attention and to …

Generating dual sequence inferences using a neural network model

V Zhong, C **ong, R Socher - US Patent 11,170,287, 2021‏ - Google Patents
A computer-implemented method for dual sequence infer ence using a neural network
model includes generating a codependent representation based on a first input represen …

Training a joint many-task neural network model using successive regularization

K Hashimoto, C **ong, R Socher - US Patent 11,042,796, 2021‏ - Google Patents
The technology disclosed provides a so-called" joint many task neural network model” to
solve a variety of increasingly complex natural language processing (NLP) tasks using …

Sequence-to-sequence prediction using a neural network model

NS Keskar, K Ahmed, R Socher - US Patent 11,928,600, 2024‏ - Google Patents
A method for sequence-to-sequence prediction using a neural network model includes
generating an encoded representation based on an input sequence using an encoder of the …

Spatial attention model for image captioning

LU Jiasen, C **ong, R Socher - US Patent 10,558,750, 2020‏ - Google Patents
The technology disclosed presents a novel spatial attention model that uses current hidden
state information of a decoder long short-term memory (LSTM) to guide attention and to …

Dynamic coattention network for question answering

C **ong, V Zhong, R Socher - US Patent 10,963,782, 2021‏ - Google Patents
The technology disclosed relates to an end-to-end neural network for question answering,
referred to herein as" dynamic coattention network (DCN)”. Roughly described, the DCN …