Search results

This setup allows to train end-to-end neural models for spoken language understanding (SLU). It uses either the Snips SLU or the Fluent Speech dataset (FSC). This framework is built using pytorch with torchaudio and the transformer package from HuggingFace. We tested using pytorch 1.5.0 and torchaudio 0.5.0.

The SageMaker handwriting recognition solution applies deep learning techniques to transcribe text in images of passages into strings. If you have your own data, you can use this solution to label your own data and train a new network with it. Endpoints are then automatically deployed with the solution.

Virtual assistants (VAs) tend to be literal in their delivery of messages. Most likely, if you ask them to deliver a message, the VAs either send a recorded message or a literal transcription to the receiver. To make incremental improvement towards a virtual assistant that you may speak to conversationally and naturally, we have provided the data necessary to build AI systems that can convert the point

This solution provides a framework for Next Generation Sequencing (NGS) genomics secondary-analysis pipelines using AWS Step Functions and AWS Batch. It deploys AWS services to develop and run custom workflow pipelines, monitor pipeline status and performance, fail-over to on-demand, handle errors, optimize for cost, and secure data with least-privileges. The solution is designed to be starting point for

Slot-filling, Translation, Intent classification, and Language identification, or STIL, is a newly-proposed task for multilingual Natural Language Understanding (NLU). By performing simultaneous slot filling and translation into a single output language (English in this case), some portion of downstream system components can be monolingual, reducing development and maintenance cost. Results are given using

This project provides an end-to-end solution for Demand Forecasting task using a new state-of-the-art Deep Learning model LSTNet available in GluonTS and Amazon SageMaker.

Embedding-based Zero-shot Retrieval through Query Generation leverages query synthesis over large corpuses of unlabeled text (such as Wikipedia) to pre-train siamese neural retrieval models. The resulting models significantly improve over previous BM25 baselines as well as state-of-the-art neural methods. This package provides support for leveraging BART-large for query synthesis as well as code for training

Although machine learning (ML) is widely used for predictive tasks, there are important scenarios in which ML cannot be used or at least cannot achieve its full potential. A major barrier to adoption is the sensitive nature of predictive queries. Individual users may lack sufficiently rich datasets to train accurate models locally but also be unwilling to send sensitive queries to commercial services that

Multi-domain dialogue state tracking (DST) is a critical component for conversational AI systems. The domain ontology (i.e., specification of domains, slots, and values) of a conversational AI system is generally incomplete, making the capability for DST models to generalize to new slots, values, and domains during inference imperative. In this paper, we propose to model multi-domain DST as a question answering

Natural language understanding (NLU) in the context of goal-oriented dialog systems typically includes intent classification and slot labeling tasks. Existing methods to expand an NLU system to new languages use machine translation with slot label projection from source to the translated utterances, and thus are sensitive to projection errors. In this work, we propose a novel end-to-end model that learns

More and more text data are becoming available these days to train Natural Language Processing models such as sentiment analysis, predictive keyboards and question-answering chatbots. If companies that deploy such models use data provided by users, they have a responsibility to take steps to ensure their users' privacy. In this solution we demonstrate how one can use Differential Privacy to build accurate

The ASK SDK v2 for Node.js makes it easier for you to build highly engaging skills by allowing you to spend more time on implementing features and less on writing boilerplate code. The ASK SDK Controls Framework (Beta) builds on the ASK SDK v2 for Node.js, providing a scalable solution for creating large, multi-turn skills in code with reusable components called controls. The ASK SMAPI SDK for Node.js provides

Homomorphic encryption is a special type of encryption scheme which enables computation of arbitrary functions on encrypted data. To evaluate a function f, a developer must implement f as a circuit F using only the "native" operation supported by the underlying homomorphic encryption scheme. Libraries which implement homomorphic encryption provide an API for these native operations which can be used to

Bort is an optimal subset of architectural parameters for the BERT architecture, extracted by applying a fully polynomial-time approximation scheme (FPTAS) for neural architecture search. Bort has an effective (that is, not counting the embedding layer) size of 5.5% the original BERT-large architecture, and 16% of the net size. It is also able to be pretrained in 288 GPU hours, which is 1.2% of the time

This guidance creates a scalable environment in AWS to prepare genomic, clinical, mutation, expression and imaging data for large-scale analysis and perform interactive queries against a data lake. This solution demonstrates how to 1) build, package, and deploy libraries used for genomics data conversion, 2) provision serverless data ingestion pipelines for multi-modal data preparation and cataloging, 3

AdaTune is a library to perform gradient based hyperparameter tuning for training deep neural networks. AdaTune currently supports tuning of the learning_rate parameter but some of the methods implemented here can be extended to other hyperparameters like momentum or weight_decay etc. AdaTune provides the following gradient based hyperparameter tuning algorithms - HD, RTHO and our newly proposed algorithm

Question Answering (QA) is in increasing demand as the amount of information available online and the desire for quick access to this content grows. A common approach to QA has been to fine-tune a pretrained language model on a task-specific labeled dataset. This paradigm, however, relies on scarce, and costly to obtain, large-scale human-labeled data. We propose an unsupervised approach to training QA

Meaning representation is an important component of semantic parsing. Although researchers have designed a lot of meaning representations, recent work focuses on only a few of them. Thus, the impact of meaning representation on semantic parsing is less understood. Furthermore, existing work’s performance is often not comprehensively evaluated due to the lack of readily-available execution engines. Upon

This repository contains all the scripts, source code, and data used for our NSDI 2020 paper on "Firecracker: Lightweight Virtualization for Serverless Applications". The ./prep directory contains scripts and other tools required to run the tests. Most tests uses minimal OS images build with linuxkit. It also contains a slightly modified version of firecracker and builds a new, statically linked binary

Many online businesses lose billions annually to fraud, but machine learning based fraud detection models can help businesses predict what interactions or users are likely fraudulent and save them from incurring those costs. In this project, we formulate the problem of fraud detection as a classification task on a heterogeneous interaction network. The machine learning model is a graph neural network (GNN