Machine Translation Weekly 96: On Evaluation of Non-Autoregressive MT Systems

I often review papers on non-autoregressive machine translation a tend the repeat the same things in my reviews. The papers often compare non-comparable things to show the non-autoregressive models in a better light. Apart from the usual flaws in MT evaluation, non-autoregressive papers often (with honorable exceptions) get lost in the knowledge distillation setup. In general, papers tend to motivate non-autoregressive MT by potential speedup. Although it is an important motivation, it is not the main motivation for me. By […]

Read more

Multi-domain Multilingual Question Answering

This post expands on the EMNLP 2021 tutorial on Multi-domain Multilingual Question Answering. The tutorial was organised by Avi Sil and me. In this post, I highlight key insights and takeaways of the tutorial. The slides are available online. You can find the table of contents below: Introduction Open-Retrieval QA vs Reading Comprehension What is a Domain? Multi-Domain QA Datasets for Multi-Domain QA Multi-Domain QA Models Multilingual QA Datasets for Multilingual QA Multilingual QA Models Open Research Directions Question answering […]

Read more

Rotates your images in the spirit of rot13

Its like rot13 but for images. Calling the algorithm imrot10 for im = image, rot = rotation, 10 = default magnitude. Unfortunately it is not symmetric like rot13 but i’m not wasting my time to develop fully symmetric so you have to use the -u parameter to undo it. python3 image-rotator.py -h usage: image-rotator.py [-h] [-i INPUT] [-o OUTPUT] [-u [UNDO]] [–magnitude MAGNITUDE] optional arguments: -h, –help show this    

Read more

A telegram bot to interact with a Minecraft Server

A telegram bot to interact with a Minecraft Server It has the following commands: /status – Returns the server status (Online/Offline). /ip – Returns the IP of the server. /uptime – Minecraft server uptime. /list – List online players. /say – Sends an ingame message to the players. /craft – Shows the crafting recipe for a certain block/item. /version – Displays the server version. /help – This help. GitHub View Github    

Read more

SAN for Product Attributes Prediction

Heterogeneous Star Graph Attention Network for Product Attributes Prediction This repository contains the official PyTorch implementation for ADVIE Paper “Heterogeneous Star Graph Attention Network for Product Attributes Prediction“.We also present the Alibaba Custermers Interaction Dataset used in this paper. Citation If you find this code or dataset is helpful, please kindly consider citing the following papers: Zhao, Xuejiao, et al. “Heterogeneous star graph attention network for product attributes prediction.” Advanced Engineering Informatics. 51, 101447. 2022.

Read more

Adversarial Differentiable Data Augmentation for Autonomous Systems

This repository provides the official PyTorch implementation of the ICRA 2021 paper: Adversarial Differentiable Data Augmentation for Autonomous SystemsAuthor: Manli Shu, Yu Shen, Ming C Lin, Tom Goldstein Environment The code has been tested on: python == 3.7.9 pytorch == 1.10.0 torchvision == 0.8.2 kornia == 0.6.2More dependencies can be found at ./requirements.txt Hardware requirements: The default training and testing setting requires 1 GPU. Data Datasets appeared in our paper can be downloaded/generated by following the directions in this page. […]

Read more

Haphazard scripts for scraping bitcoin/bitcoin data from GitHub

This is a quick-and-dirty tool used to scrape bitcoin/bitcoin pull request andcommentary data. Each output/ folder contains comments.json: an aggregated list of both issue and review comments, in Github’soriginal format commits.json: a list of commit objects corresponding to the PR, in Github’soriginal format pr.json: the pull request object, in Github’s original format comments_abbrev.csv: abbreviated representation of each comment in CSV format pr_abbrev.csv: abbreviated representation of the PR in CSV format done: the datetime we retrieved the PR data Limitations Right […]

Read more
1 315 316 317 318 319 916