Kaiqiang Song's Projects
Academic Responsive (AR) Website Template
Tools for checking ACL paper submissions
Small and easy C++ AdaBoost Implementation
Fully-automated scripts for collecting AI-related papers
A python package of common operations for AMRs
A curated list of reinforcement learning with human feedback resources (continually updated)
The Berkeley Document Summarizer is a learning-based, single-document summarization system that extracts source document content, exploits syntactic information to compress it, and uses coreference constraints to ensure clarity.
TensorFlow code and pre-trained models for BERT
ACL 2022: BRIO: Bringing Order to Abstractive Summarization
For 2017 Fall, CAP5415_Computer Vision Program Assignments
For 2017 Fall, CAP6676 Knowledge Representation Assignments
code for paper "CATE: Computation-aware Neural Architecture Encoding with Transformers"
Lightweight package for interacting with ChatGPT's API by OpenAI. Uses reverse engineered official API.
(AAAI'20) The source code for the paper "Controlling the Amount of Verbatim Copying in Abstractive Summarization".
CPT: A Pre-Trained Unbalanced Transformer for Both Chinese Language Understanding and Generation
Implementation of DALL-E 2, OpenAI's updated text-to-image synthesis neural network, in Pytorch
The unified platform for data-related resources.
DeepSpeech is an open source embedded (offline, on-device) speech-to-text engine which can run in real time on devices ranging from a Raspberry Pi 4 to high power GPU servers.
Example models using DeepSpeed
code for document level AMR representation and evaluation
Evaluation as a Service for NLP