Almond is an extendible open-source virtual assistant designed to help people access Internet services and IoT (Internet of Things) devices. Both are referred to as skills here. Service providers can easily enable their devices for Almond by defining proper APIs (Application Programming Interfaces) for ThingTalk in Thingpedia. ThingTalk is a virtual assistant programming language, and Thingpedia is an application encyclopedia. Almond uses a large neural network to translate user commands in natural language into ThingTalk programs. To obtain enough data for the training of the neural network, Genie was developed to synthesize pairs of user commands and corresponding ThingTalk programs based on a natural language template approach. In this work, we extended Genie to support Chinese. For 107 devices and 261 functions registered in Thingpedia, 649 Chinese primitive templates and 292 Chinese construct templates were analyzed and developed. Two models, seq2seq (sequence-to-sequence) and MQAN (multiple question answer network), were trained to translate user commands in Chinese into ThingTalk programs. Both models were evaluated, and the experiment results showed that MQAN outperformed seq2seq. The exact match, BLEU, and F1 token accuracy of MQAN were 0.7, 0.82, and 0.88, respectively. As a result, users could use Chinese in Almond to access Internet services and IoT devices registered in Thingpedia.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8915006 | PMC |
| http://dx.doi.org/10.3390/s22051891 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Comparative assessment of a virtual performance measure with self-report and performance-based outcomes in patients with hip osteoarthritis.
BMC Musculoskelet Disord
January 2025
Sunnybrook Research Institute, Sunnybrook Health Sciences Centre, Toronto, Canada.
Background: The purposes of this study were to examine the reliability and factorial and convergent validity of a virtual performance measure (VPM) in patients with osteoarthritis (OA) of the hip joint and to compare the known-group validity of the VPM with traditional self-report and performance-based outcomes.
Methods: The VPM score was based on the results of 10 videos showing increasing difficulty in performing specific functional tasks. Patients were requested to choose the video that best reflected their own level of function.
Tape-Assisted Residual Layer-Free One-Step Nanoimprinting of High-Index Hybrid Polymer for Optical Loss-Suppressed Metasurfaces.
Adv Sci (Weinh)
January 2025
Department of Mechanical Engineering, Pohang University of Science and Technology (POSTECH), Pohang, 37673, Republic of Korea.
The commercialization of metasurfaces is crucial for real-world applications such as wearable sensors, pigment-free color pixels, and augmented and virtual reality devices. Nanoparticle-embedded resin-based nanoimprint lithography (PER-NIL) has shown itself to be a low-cost, high-throughput manufacturing method enabling the replication of high-index nanostructures. It has been extensively integrated into the fabrication of hologram metasurfaces, metalenses, and sensors due to its procedural simplicity.
View Article and Find Full Text PDFBarriers and enablers to engagement with a type 2 diabetes remission project in the North East of England: qualitative perspectives of patients.
J Nutr Sci
January 2025
School of Health & Life Sciences, Teesside University, Middlesbrough, UK.
This qualitative research sought to identify factors influencing patient choice of, and patient-related internal and external enablers and barriers to engagement with, type 2 diabetes (T2D) remission strategies offered by the Remission in diabetes (REMI.D) project. Patients had a choice of three diets: Total Diet Replacement (TDR)-Formula Food Products, TDR-Food, and Healthy lifestyle approach; and three activity pathways: Everyday life, General Practitioner referral, and Social hub.
View Article and Find Full Text PDFGeneration of deep learning based virtual non-contrast CT using dual-layer dual-energy CT and its application to planning CT for radiotherapy.
PLoS One
January 2025
Department of Radiation Oncology, Seoul National University Hospital, Seoul, Republic of Korea.
This paper presents a novel approach for generating virtual non-contrast planning computed tomography (VNC-pCT) images from contrast-enhanced planning CT (CE-pCT) scans using a deep learning model. Unlike previous studies, which often lacked sufficient data pairs of contrast-enhanced and non-contrast CT images, we trained our model on dual-energy CT (DECT) images, using virtual non-contrast CT (VNC CT) images as outputs instead of true non-contrast CT images. We used a deterministic method to convert CE-pCT images into pseudo DECT images for model application.
View Article and Find Full Text PDFDeep learning-based encryption scheme for medical images using DCGAN and virtual planet domain.
Sci Rep
January 2025
Department of Computer Science and Information Systems, Birla Institute of Technology and Science-Pilani, Hyderabad Campus, Hyderabad, 500078, India.
The motivation for this article stems from the fact that medical image security is crucial for maintaining patient confidentiality and protecting against unauthorized access or manipulation. This paper presents a novel encryption technique that integrates the Deep Convolutional Generative Adversarial Networks (DCGAN) and Virtual Planet Domain (VPD) approach to enhance the protection of medical images. The method uses a Deep Learning (DL) framework to generate a decoy image, which forms the basis for generating encryption keys using a timestamp, nonce, and 1-D Exponential Chebyshev map (1-DEC).
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!