KaiQiangSong
Senior Research Scientist @ Tencent AI Lab, Interested in NLP, LLM, Text Generation, and Summarization. Hiring Interns
Tencent AI LabBellevue, WA
Pinned Repositories
CAP5415_ComputerVision
For 2017 Fall, CAP5415_Computer Vision Program Assignments
CATE
code for paper "CATE: Computation-aware Neural Architecture Encoding with Transformers"
constituency-parsing-visualization
control-over-copying
(AAAI'20) The source code for the paper "Controlling the Amount of Verbatim Copying in Abstractive Summarization".
joint_parse_summ
(AAAI'20) The source code for the paper "Joint Parsing and Generation for Abstractive Summarization".
struct_infused_summ
(COLING'18) The source code for the paper "Structure-Infused Copy Mechanisms for Abstractive Summarization".
varying-length-summ
We provide the source code for the paper "A New Approach to Overgenerating and Scoring Abstractive Summaries" accepted at NAACL'21. If you find the code useful, please cite the following paper.
GrndPodcastSum
(ACL 2022) The source code for the paper "Towards Abstractive Grounded Summarization of Podcast Transcripts"
season
[EMNLP 2022] Salience Allocation as Guidance for Abstractive Summarization
control-over-copying
(AAAI'20) The source code for the paper "Controlling the Amount of Verbatim Copying in Abstractive Summarization".
KaiQiangSong's Repositories
KaiQiangSong/multilingual-rouge
A multilingual rouge package (followed rouge_score) using BPE-tokenizer (from huggingface)
KaiQiangSong/pl-training
KaiQiangSong/InfoBench
KaiQiangSong/nlp_chinese_corpus
大规模中文自然语言处理语料 Large Scale Chinese Corpus for NLP
KaiQiangSong/season
[EMNLP 2022] Salience Allocation as Guidance for Abstractive Summarization
KaiQiangSong/AI-Paper-Collector
Fully-automated scripts for collecting AI-related papers
KaiQiangSong/awesome-RLHF
A curated list of reinforcement learning with human feedback resources (continually updated)
KaiQiangSong/ChatGPT
Lightweight package for interacting with ChatGPT's API by OpenAI. Uses reverse engineered official API.
KaiQiangSong/DALLE2-pytorch
Implementation of DALL-E 2, OpenAI's updated text-to-image synthesis neural network, in Pytorch
KaiQiangSong/DataLab
The unified platform for data-related resources.
KaiQiangSong/DeepSpeech
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.
KaiQiangSong/DeepSpeedExamples
Example models using DeepSpeed
KaiQiangSong/diffusers
KaiQiangSong/docAMR
code for document level AMR representation and evaluation
KaiQiangSong/flash-attention
Fast and memory-efficient exact attention
KaiQiangSong/gitignore
A collection of useful .gitignore templates
KaiQiangSong/gpt-crawler
Crawl a site to generate knowledge files to create your own custom GPT from a URL
KaiQiangSong/helm
Holistic Evaluation of Language Models (HELM), a framework to increase the transparency of language models (https://arxiv.org/abs/2211.09110).
KaiQiangSong/knn-transformers
PyTorch code for the RetoMaton paper: "Neuro-Symbolic Language Modeling with Automaton-augmented Retrieval" (ICML 2022), including an implementation of kNN-LM and kNN-MT
KaiQiangSong/LLaMA-Megatron-DeepSpeed
Ongoing research training transformer language models at scale, including: BERT & GPT-2
KaiQiangSong/LLMDataHub
A quick guide (especially) for trending instruction finetuning datasets
KaiQiangSong/lm-evaluation-harness
A framework for few-shot evaluation of autoregressive language models.
KaiQiangSong/long-range-arena
Long Range Arena for Benchmarking Efficient Transformers
KaiQiangSong/narrasum
KaiQiangSong/nlp-in-ling
Natural Language Processing Research in North American Linguistics Departments
KaiQiangSong/NLPDataSet
记录本人整理的一些数据集
KaiQiangSong/summarization-datasets
Pre-processing and in some cases downloading of datasets for the paper "Content Selection in Deep Learning Models of Summarization."
KaiQiangSong/theme-academic-cv
KaiQiangSong/transformer-ls
Official implementation of Long-Short Transformer in PyTorch.
KaiQiangSong/transformers-bloom-inference
Fast Inference Solutions for BLOOM