Search results

Semantic parsing is an important NLP problem, particularly for voice assistants such as Alexa and Google Assistant. State-of-the-art (SOTA) semantic parsers are seq2seq architectures based on large language models that have been pretrained on vast amounts of text. To better leverage that pretraining, recent work has explored a reformulation of semantic parsing whereby the output sequences are themselves

The Alexa Voice Service (AVS) enables developers to integrate Alexa directly into their products, bringing the convenience of voice control to any connected device. AVS provides developers with access to a suite of resources to build Alexa-enabled products, including APIs, hardware development kits, software development kits, and documentation.

Leveraging the characteristics of convolutional layers, neural networks are extremely effective for pattern recognition tasks. However in some cases, their decisions are based on unintended information leading to high performance on standard benchmarks but also to a lack of generalization to challenging testing conditions and unintuitive failures. Recent work has termed this ”shortcut learning” and addressed

Pre-trained language models (PLM) have advanced the state-of-the-art across NLP applications, but lack domain-specific knowledge that does not naturally occur in pre-training data. Previous studies augmented PLMs with symbolic knowledge for different downstream NLP tasks. However, knowledge bases (KBs) utilized in these studies are usually large-scale and static, in contrast to small, domain-specific, and

The FoodOrdering dataset is a task-oriented parsing dataset in the food-ordering domain with utterances and annotations derived from the menus of five venues characteristic of that business vertical: burgers, burritos, coffees, pizzas, and subs.

A 20 billion parameter multilingual seq2seq model called Alexa Teacher Model (AlexaTM 20B), which achieves state-of-the-art (SOTA) performance on 1-shot summarization tasks, outperforming a much larger 540B PaLM decoder model. AlexaTM 20B also achieves SOTA in 1-shot machine translation, especially for low-resource languages, across almost all language pairs supported by the model (Arabic, English, French

Automatic speech recognition (ASR) is increasingly being used in specialized domains such as medical ASR and news transcription. Owing to the lack of high quality annotated speech data in such domains, off-the-shelf models are commonly employed by fine-tuning on domain-specific data. This poses a significant challenge in transcribing long-tail expressions and out-of-vocabulary (OOV) named entities. On the

Current question answering (QA) systems primarily consider the single-answer scenario, where each question is assumed to be paired with one correct answer. However, in many real-world QA applications, multiple answer scenarios arise where consolidating answers into a comprehensive and non-redundant set of answers is a more efficient user interface. In this paper, we formulate the problem of answer consolidation

Project Description This is a test framework for the bias bounties project. Getting Started as a Bounty Hunter If you are interacting with this codebase as a "bounty hunter", you'll need to have a way to run Jupyter notebooks. The easiest way to do this is to download Anaconda, which will also manage all of your python packages for you. See here for installation instructions: https://docs.anaconda.com/anaconda

This module implements a set of functions to perform MAXENT from a causal perspective. The code here can be used to reproduce the results in the publication Obtaining Causal Information by Merging Datasets with MAXENT. The parts of the plots using KCI are, unfortunately, not available. To reproduce the results in the article create a python 3.6+ environment, pip install all the requirements.txt file and

As generic machine translation (MT) quality has improved, the need for targeted benchmarks that explore fine-grained aspects of quality has increased (Freitag et al., 2021; Isabelle et al., 2017). In particular, gender accuracy in translation (Choubey et al., 2021; Saunders and Byrne, 2020) can have implications in terms of output fluency, translation accuracy, and ethics. In this paper, we introduce MTGenEval

Robots operating in human spaces must be able to engage in natural language interaction, both understanding and executing instructions, and using conversation to resolve ambiguity and correct mistakes. To study this, we introduce TEACh, a dataset of over 3,000 human–human, interactive dialogues to complete household tasks in simulation. A Commander with access to oracle information about a task communicates

Skill Components are “ready to use” experiences that you can easily add to your skills, and configure them according to your needs. Each component is a collection of skill primitives, such as VUI dialogs & intents, Alexa Presentation Language (APL) documents, skill code, skill connection tasks, and skill events. They bring together design best practices and pre-built voice experiences, which solve for a

Fault-tolerant protocols and quantum error correction (QEC) are essential to building reliable quantum computers from imperfect components that are vulnerable to errors. Optimizing the resource and time overheads needed to implement QEC is one of the most pressing challenges. Here, we introduce a new topological quantum error-correcting code, the three-dimensional subsystem toric code (3D STC). The 3D STC

Universal fault-tolerant quantum computers will require the use of efficient protocols to implement encoded operations necessary in the execution of algorithms. In this work, we show how SMT solvers can be used to automate the construction of Clifford circuits with certain fault-tolerance properties and we apply our techniques to a fault-tolerant magic-state-preparation protocol. Part of the protocol requires

We propose a protocol for the deterministic generation of entanglement between two ensembles of nuclear spins surrounding two distant quantum dots. The protocol relies on the injection of electrons with definite polarization, their sequential interaction with the nuclear ensembles of each quantum dot for a short time, and the coherent transfer of each electron from one quantum dot to the other. Computing

Divergence chain rules for channels relate the divergence of a pair of channel inputs to the divergence of the corresponding channel outputs. An important special case of such a rule is the data-processing inequality, which tells us that if the same channel is applied to both inputs then the divergence cannot increase. Based on direct matrix analysis methods, we derive several Rényi divergence chain rules

Light is a powerful tool for controlling mechanical motion, as shown by numerous applications in the field of cavity optomechanics. Recently, small scale optomechanical circuits, connecting a few optical and mechanical modes, have been demonstrated in an ongoing push towards multi-mode on-chip optomechanical systems. An ambitious goal driving this trend is to produce topologically protected phonon transport

Quantum technology promises to revolutionize how we learn about the physical world. An experiment that processes quantum data with a quantum computer could have substantial advantages over conventional experiments in which quantum states are measured and outcomes are processed with a classical computer. We proved that quantum machines could learn from exponentially fewer experiments than the number required

Lattice surgery is a measurement-based technique for performing fault-tolerant quantum computation in two dimensions. When using the surface code, the most general lattice surgery operations require lattice irregularities called twist defects. However, implementing twist-based lattice surgery may require additional resources, such as extra device connectivity, and could lower the threshold and overall performance