公开(公告)号：US20210279414A1

公开(公告)日：2021-09-09

申请号：US16810345

申请日：2020-03-05

Applicant: ADOBE INC.

Inventor： KHALIL MRINI ,  WALlTER CHANG ,  TRUNG BUI ,  QUAN TRAN ,  FRANCK DERNONCOURT

IPC: G06F40/211 ,  G06N3/04 ,  G06N3/08

Abstract: Systems and methods for parsing natural language sentences using an artificial neural network (ANN) are described. Embodiments of the described systems and methods may generate a plurality of word representation matrices for an input sentence, wherein each of the word representation matrices is based on an input matrix of word vectors, a query vector, a matrix of key vectors, and a matrix of value vectors, and wherein a number of the word representation matrices is based on a number of syntactic categories, compress each of the plurality of word representation matrices to produce a plurality of compressed word representation matrices, concatenate the plurality of compressed word representation matrices to produce an output matrix of word vectors, and identify at least one word from the input sentence corresponding to a syntactic category based on the output matrix of word vectors.

公开(公告)号：US20220277186A1

公开(公告)日：2022-09-01

申请号：US17186566

申请日：2021-02-26

Applicant: ADOBE INC.

Inventor： QUAN TRAN ,  Franck Dernoncourt ,  Walter Chang

IPC: G06N3/04 ,  G06N3/08 ,  G06F16/242

Abstract: The present disclosure describes systems and methods for dialog processing and information retrieval. Embodiments of the present disclosure provide a dialog system (e.g., a task-oriented dialog system) with adaptive recurrent hopping and dual context encoding to receive and understand a natural language query from a user, manage dialog based on natural language conversation, and generate natural language responses. For example, a memory network can employ a memory recurrent neural net layer and a decision meta network (e.g., a subnet) to determine an adaptive number of memory hops for obtaining readouts from a knowledge base. Further, in some embodiments, a memory network uses a dual context encoder to encode information from original context and canonical context using parallel encoding layers.

公开(公告)号：US20220179848A1

公开(公告)日：2022-06-09

申请号：US17116640

申请日：2020-12-09

Applicant: ADOBE INC.

Inventor： QUAN TRAN ,  Walter Chang ,  Franck Dernoncourt

IPC: G06F16/242 ,  G06N3/08 ,  H04L12/58 ,  G06F40/40

Abstract: The present disclosure provides a memory-based neural network for question answering. Embodiments of the disclosure identify meta-evidence nodes in an embedding space, where the meta-evidence nodes represent salient features of a training set. Each element of the training set may include a questions appended to a ground truth answer. The training set may also include questions with wrong answers that are indicated as such. In some examples, a neural Turing machine (NTM) reads a dataset and summarizes the dataset into a few meta-evidence nodes. A subsequent question may be appended to multiple candidate answers to form an input phrase, which may also be embedded in the embedding space. Then, corresponding weights may be identified for each of the meta-evidence nodes. The embedded input phrase and the weighted meta-evidence nodes may be used to identify the most appropriate answer.