Songbin's repositories
bert-cosine-sim
Fine-tune BERT to generate sentence embedding for cosine similarity
attention-is-all-you-need-pytorch
A PyTorch implementation of the Transformer model in "Attention is All You Need".
bert
TensorFlow code and pre-trained models for BERT
BERT-NER
Pytorch-Named-Entity-Recognition-with-BERT
capsnet_pytorch
PyTorch implementation of Geoffrey Hinton's Dynamic Routing Between Capsules
ComiRec
Source code and dataset for KDD 2020 paper "Controllable Multi-Interest Framework for Recommendation"
d2l-en
Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 400 universities from 60 countries including Stanford, MIT, Harvard, and Cambridge.
deepo
Set up deep learning environment in a single command line.
DeepPavlov
An open source library for deep learning end-to-end dialog systems and chatbots.
examples
A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.
fairseq
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
few-shot
Repository for few-shot learning machine learning projects
GLUE-baselines
[DEPRECATED] Repo for exploring multi-task learning approaches to learning sentence representations
gpt-2-simple
Python package to easily retrain OpenAI's GPT-2 text-generating model on new texts
Megatron-LM
Ongoing research training transformer language models at scale, including: BERT
mt-dnn
Multi-Task Deep Neural Networks for Natural Language Understanding
multi_armed_thompson
python module to solve the multi armed bandit problem with Thompson sampling
OpenKP
Automatically extracting keyphrases that are salient to the document meanings is an essential step to semantic document understanding. An effective keyphrase extraction (KPE) system can benefit a wide range of natural language processing and information retrieval tasks. Recent neural methods formulate the task as a document-to-keyphrase sequence-to-sequence task. These seq2seq learning models have shown promising results compared to previous KPE systems The recent progress in neural KPE is mostly observed in documents originating from the scientific domain. In real-world scenarios, most potential applications of KPE deal with diverse documents originating from sparse sources. These documents are unlikely to include the structure, prose and be as well written as scientific papers. They often include a much diverse document structure and reside in various domains whose contents target much wider audiences than scientists. To encourage the research community to develop a powerful neural model with key phrase extraction on open domains we have created OpenKP: a dataset of over 150,000 documents with the most relevant keyphrases generated by expert annotation.
paraphrase_identification
Examine two sentences and determine whether they have the same meaning.
pytext
A natural language modeling framework based on PyTorch
pytorch-pretrained-BERT
đź“–The Big-&-Extending-Repository-of-Transformers: Pretrained PyTorch models for Google's BERT, OpenAI GPT & GPT-2, Google/CMU Transformer-XL.
RecSys2019_DeepLearning_Evaluation
This is the repository of our article published in RecSys 2019 "Are We Really Making Much Progress? A Worrying Analysis of Recent Neural Recommendation Approaches"
siamese-triplet
Siamese and triplet networks with online pair/triplet mining in PyTorch
subword-nmt
Unsupervised Word Segmentation for Neural Machine Translation and Text Generation
thompson
Thompson Sampling Tutorial
xlnet
XLNet: Generalized Autoregressive Pretraining for Language Understanding
xtreme
XTREME is a benchmark for the evaluation of the cross-lingual generalization ability of pre-trained multilingual models that covers 40 typologically diverse languages and includes nine tasks.