A Theoretical Analysis of the Repetition Problem in Text Generation

This repository share the code for the paper “A Theoretical Analysis of the Repetition Problem in Text Generation” in AAAI 2021. The repetition problem has been observed in nearly all text generation models. We theoretically prove that this problem is, unfortunately, caused by the traits of our language itself. There exists too many words predicting the same word as the subsequent word with high probability. Consequently, it is easy to go back to that word and form repetitions. We dub […]

Read more

Zulip server and webapp: powerful open source team chat

Zulip is a powerful, open source group chat application that combines the immediacy of real-time chat with the productivity benefits of threaded conversations. Zulip is used by open source projects, Fortune 500 companies, large standards bodies, and others who need a real-time chat system that allows users to easily process hundreds or thousands of messages a day. With over 700 contributors merging over 500 commits a month, Zulip is also the largest and fastest growing open source group chat project.

Read more

Easy-to-use and powerful offline translation tool

Introduction Virtaal is a graphical program for doing translation. It is meant to be easy to use and powerful at the same time. Although the initial focus is on software translation (localisation or l10n), we definitely intend it to be useful for several purposes. References Installation The easiest way for most users to install Virtaal is through the provided packages, or through the packaging system of their distribution. On the Virtaal website there should be packages for Windows and several […]

Read more

Synapse: Matrix reference homeserver

Matrix is an ambitious new ecosystem for open federated Instant Messaging and VoIP. The basics you need to know to get up and running are: Everything in Matrix happens in a room. Rooms are distributed and do not exist on any single server. Rooms can be located using convenience aliases like #matrix:matrix.org or #test:localhost:8448. Matrix user IDs look like @matthew:matrix.org (although in the future you will normally refer to yourself and others using a third party identifier (3PID): email address, […]

Read more

Aan open-source whistleblower submission system

SecureDrop is an open-source whistleblower submission system that media organizations can use to securely accept documents from, and communicate with anonymous sources. It was originally created by the late Aaron Swartz and is currently managed by the Freedom of the Press Foundation. Documentation SecureDrop’s documentation is built and hosted by Read the Docs at https://docs.securedrop.org. It is maintained in a standalone repository: https://github.com/freedomofpress/securedrop-docs By default, the documentation describes the most recent SecureDrop release. This is known as the stable   […]

Read more

Python 3.10: Cool New Features for You to Try

Python 3.10 is out! Volunteers have been working on the new version since May 2020 to bring you a better, faster, and more secure Python. As of October 4, 2021, the first official version is available. Each new version of Python brings a host of changes. You can read about all of them in the documentation. Here, you’ll get to learn about the coolest new features. In this tutorial, you’ll learn about: Debugging with more helpful and precise error messages […]

Read more
1 2