FasterTransformerTransformer related optimization, including BERT, GPT
Stars: ✭ 1,571 (+2280.3%)
FinBERT-QAFinancial Domain Question Answering with pre-trained BERT Language Model
Stars: ✭ 70 (+6.06%)
TabFormerCode & Data for "Tabular Transformers for Modeling Multivariate Time Series" (ICASSP, 2021)
Stars: ✭ 209 (+216.67%)
npo classifierAutomated coding using machine-learning and remapping the U.S. nonprofit sector: A guide and benchmark
Stars: ✭ 18 (-72.73%)
SA-BERTCIKM 2020: Speaker-Aware BERT for Multi-Turn Response Selection in Retrieval-Based Chatbots
Stars: ✭ 71 (+7.58%)
R-ATRegularized Adversarial Training
Stars: ✭ 19 (-71.21%)
CLSPCode and data for EMNLP 2018 paper "Cross-lingual Lexical Sememe Prediction"
Stars: ✭ 19 (-71.21%)
Kaleido-BERT(CVPR2021) Kaleido-BERT: Vision-Language Pre-training on Fashion Domain.
Stars: ✭ 252 (+281.82%)
CLUE pytorchCLUE baseline pytorch CLUE的pytorch版本基线
Stars: ✭ 72 (+9.09%)
ganbertEnhancing the BERT training with Semi-supervised Generative Adversarial Networks
Stars: ✭ 205 (+210.61%)
Cool-NLPCVSome Cool NLP and CV Repositories and Solutions (收集NLP中常见任务的开源解决方案、数据集、工具、学习资料等)
Stars: ✭ 143 (+116.67%)
BiPaRThis repository contains datasets (including testing set) for EMNLP-IJCNLP 2019 paper "BiPaR: A Bilingual Parallel Dataset for Multilingual and Cross-lingual Reading Comprehension on Novels"
Stars: ✭ 20 (-69.7%)
PromptPapersMust-read papers on prompt-based tuning for pre-trained language models.
Stars: ✭ 2,317 (+3410.61%)
co-attentionPytorch implementation of "Dynamic Coattention Networks For Question Answering"
Stars: ✭ 54 (-18.18%)
DiscEvalDiscourse Based Evaluation of Language Understanding
Stars: ✭ 18 (-72.73%)
PersianQAPersian (Farsi) Question Answering Dataset (+ Models)
Stars: ✭ 114 (+72.73%)
beirA Heterogeneous Benchmark for Information Retrieval. Easy to use, evaluate your models across 15+ diverse IR datasets.
Stars: ✭ 738 (+1018.18%)
extractive rc by runtime mtCode and datasets of "Multilingual Extractive Reading Comprehension by Runtime Machine Translation"
Stars: ✭ 36 (-45.45%)
Transformers🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
Stars: ✭ 55,742 (+84357.58%)
BERTOverflowA Pre-trained BERT on StackOverflow Corpus
Stars: ✭ 40 (-39.39%)
Pytorch Sentiment AnalysisTutorials on getting started with PyTorch and TorchText for sentiment analysis.
Stars: ✭ 3,209 (+4762.12%)
TexarToolkit for Machine Learning, Natural Language Processing, and Text Generation, in TensorFlow. This is part of the CASL project: http://casl-project.ai/
Stars: ✭ 2,236 (+3287.88%)
LAMB Optimizer TFLAMB Optimizer for Large Batch Training (TensorFlow version)
Stars: ✭ 119 (+80.3%)
KashgariKashgari is a production-level NLP Transfer learning framework built on top of tf.keras for text-labeling and text-classification, includes Word2Vec, BERT, and GPT2 Language Embedding.
Stars: ✭ 2,235 (+3286.36%)
mixed-language-trainingAttention-Informed Mixed-Language Training for Zero-shot Cross-lingual Task-oriented Dialogue Systems (AAAI-2020)
Stars: ✭ 29 (-56.06%)
Clue中文语言理解测评基准 Chinese Language Understanding Evaluation Benchmark: datasets, baselines, pre-trained models, corpus and leaderboard
Stars: ✭ 2,425 (+3574.24%)
Transformer-QG-on-SQuADImplement Question Generator with SOTA pre-trained Language Models (RoBERTa, BERT, GPT, BART, T5, etc.)
Stars: ✭ 28 (-57.58%)
Awesome Bertbert nlp papers, applications and github resources, including the newst xlnet , BERT、XLNet 相关论文和 github 项目
Stars: ✭ 1,732 (+2524.24%)
iamQA中文wiki百科QA阅读理解问答系统,使用了CCKS2016数据的NER模型和CMRC2018的阅读理解模型,还有W2V词向量搜索,使用torchserve部署
Stars: ✭ 46 (-30.3%)
Fast BertSuper easy library for BERT based NLP models
Stars: ✭ 1,678 (+2442.42%)
banglabertThis repository contains the official release of the model "BanglaBERT" and associated downstream finetuning code and datasets introduced in the paper titled "BanglaBERT: Language Model Pretraining and Benchmarks for Low-Resource Language Understanding Evaluation in Bangla" accpeted in Findings of the Annual Conference of the North American Chap…
Stars: ✭ 186 (+181.82%)
ChineseglueLanguage Understanding Evaluation benchmark for Chinese: datasets, baselines, pre-trained models,corpus and leaderboard
Stars: ✭ 1,548 (+2245.45%)
NLPDataAugmentationChinese NLP Data Augmentation, BERT Contextual Augmentation
Stars: ✭ 94 (+42.42%)
Nlp TutorialNatural Language Processing Tutorial for Deep Learning Researchers
Stars: ✭ 9,895 (+14892.42%)
Chinese Bert WwmPre-Training with Whole Word Masking for Chinese BERT(中文BERT-wwm系列模型)
Stars: ✭ 6,357 (+9531.82%)
neuro-comma🇷🇺 Punctuation restoration production-ready model for Russian language 🇷🇺
Stars: ✭ 46 (-30.3%)
Bert PytorchGoogle AI 2018 BERT pytorch implementation
Stars: ✭ 4,642 (+6933.33%)
sticker2Further developed as SyntaxDot: https://github.com/tensordot/syntaxdot
Stars: ✭ 14 (-78.79%)
Bert Bilstm Crf NerTensorflow solution of NER task Using BiLSTM-CRF model with Google BERT Fine-tuning And private Server services
Stars: ✭ 3,838 (+5715.15%)
wisdomifyA BERT-based reverse dictionary of Korean proverbs
Stars: ✭ 95 (+43.94%)
BERT-QECode and resources for the paper "BERT-QE: Contextualized Query Expansion for Document Re-ranking".
Stars: ✭ 43 (-34.85%)
T3[EMNLP 2020] "T3: Tree-Autoencoder Constrained Adversarial Text Generation for Targeted Attack" by Boxin Wang, Hengzhi Pei, Boyuan Pan, Qian Chen, Shuohang Wang, Bo Li
Stars: ✭ 25 (-62.12%)
OpenUEOpenUE是一个轻量级知识图谱抽取工具 (An Open Toolkit for Universal Extraction from Text published at EMNLP2020: https://aclanthology.org/2020.emnlp-demos.1.pdf)
Stars: ✭ 274 (+315.15%)
PIEFast + Non-Autoregressive Grammatical Error Correction using BERT. Code and Pre-trained models for paper "Parallel Iterative Edit Models for Local Sequence Transduction": www.aclweb.org/anthology/D19-1435.pdf (EMNLP-IJCNLP 2019)
Stars: ✭ 164 (+148.48%)
BertSimilarityComputing similarity of two sentences with google's BERT algorithm。利用Bert计算句子相似度。语义相似度计算。文本相似度计算。
Stars: ✭ 348 (+427.27%)
gplPowerful unsupervised domain adaptation method for dense retrieval. Requires only unlabeled corpus and yields massive improvement: "GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrieval" https://arxiv.org/abs/2112.07577
Stars: ✭ 216 (+227.27%)
NAG-BERT[EACL'21] Non-Autoregressive with Pretrained Language Model
Stars: ✭ 47 (-28.79%)
wechselCode for WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of monolingual language models.
Stars: ✭ 39 (-40.91%)
DE-LIMITDeEpLearning models for MultIlingual haTespeech (DELIMIT): Benchmarking multilingual models across 9 languages and 16 datasets.
Stars: ✭ 90 (+36.36%)
CAIL法研杯CAIL2019阅读理解赛题参赛模型
Stars: ✭ 34 (-48.48%)
TriB-QA吹逼我们是认真的
Stars: ✭ 45 (-31.82%)