Search results

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

Models and code for deep learning representations developed by the AWS AI Speech team: DeCoAR (self-supervised contextual representations for speech recognition) BERTphone (phonetically-aware acoustic BERT for speaker and language recognition) DeCoAR 2.0 (deep contextualized acoustic representation with vector quantization)

This solution detects product defects with an end-to-end Deep Learning workflow for quality control in manufacturing process. The solution takes input of product images and identifies defect regions with bounding boxes. In particular, this solution takes two distinct approaches: Use an implementation of the Defect Detection Network (DDN) algorithm following An End-to-End Steel Surface Defect Detection on

Knowledge graphs (KGs) are ubiquitous structures for information storage in several real-world applications such as web search, ecommerce, social networks, and biology. Querying KGs remains a foundational and challenging problem due to their size and complexity. Promising approaches to tackle this problem include embedding the KG units (e.g., entities and relations) in a Euclidean space such that the query

A long-standing goal of task-oriented dialogue research is the ability to flexibly adapt dialogue models to new domains. To progress research in this direction, we introduce DialoGLUE (Dialogue Language Understanding Evaluation), a public benchmark consisting of 7 task-oriented dialogue datasets covering 4 distinct natural language understanding tasks, designed to encourage dialogue research in representation-based

Learning unsupervised node embeddings facilitates several downstream tasks such as node classification and link prediction. A node embedding is universal if it is designed to be used by and benefit various downstream tasks. This work introduces PanRep, a graph neural network (GNN) model, for unsupervised learning of universal node representations for heterogenous graphs. PanRep consists of a GNN encoder

Language model based pre-trained models such as BERT have provided significant gains across different NLP tasks. In this paper, we study different types of transformer based pretrained models such as auto-regressive models (GPT-2), auto-encoder models (BERT), and seq2seq models (BART) for conditional data augmentation. We show that prepending the class labels to text sequences provides a simple yet effective

Large transformer-based language models have been shown to be very effective in many classification tasks. However, their computational complexity prevents their use in applications requiring the classification of a large set of candidates. While previous works have investigated approaches to reduce model size, relatively little attention has been paid to techniques to improve batch throughput during inference

The SG-NLG dataset is a pre-processed version of the DSTC8 Schema-Guided Dialogue SGD dataset, designed specifically for data-to-text NLG. The original DSTC8 SGD contains ~20,000 dialogues spanning across ~20 domains. This SG-NLG dataset is designed to make it easier to conduct NLG experiments on the SGD data. We pre-process SGD by pairing the schema for each system turn with the corresponding set of natural