ChinesenlpDatasets, SOTA results of every fields of Chinese NLP
Stars: ✭ 1,206 (+2521.74%)
NER-FunTool本NER项目包含多个中文数据集,模型采用BiLSTM+CRF、BERT+Softmax、BERT+Cascade、BERT+WOL等,最后用TFServing进行模型部署,线上推理和线下推理。
Stars: ✭ 56 (+21.74%)
Farm🏡 Fast & easy transfer learning for NLP. Harvesting language models for the industry. Focus on Question Answering.
Stars: ✭ 1,140 (+2378.26%)
hard-label-attackNatural Language Attacks in a Hard Label Black Box Setting.
Stars: ✭ 26 (-43.48%)
deformer[ACL 2020] DeFormer: Decomposing Pre-trained Transformers for Faster Question Answering
Stars: ✭ 111 (+141.3%)
Bidaf KerasBidirectional Attention Flow for Machine Comprehension implemented in Keras 2
Stars: ✭ 60 (+30.43%)
Cross-Lingual-MRCCross-Lingual Machine Reading Comprehension (EMNLP 2019)
Stars: ✭ 66 (+43.48%)
bert-as-a-service TFXEnd-to-end pipeline with TFX to train and deploy a BERT model for sentiment analysis.
Stars: ✭ 32 (-30.43%)
Cdqa Annotator⛔ [NOT MAINTAINED] A web-based annotator for closed-domain question answering datasets with SQuAD format.
Stars: ✭ 48 (+4.35%)
wechselCode for WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of monolingual language models.
Stars: ✭ 39 (-15.22%)
PersianQAPersian (Farsi) Question Answering Dataset (+ Models)
Stars: ✭ 114 (+147.83%)
text2classMulti-class text categorization using state-of-the-art pre-trained contextualized language models, e.g. BERT
Stars: ✭ 15 (-67.39%)
SpagoSelf-contained Machine Learning and Natural Language Processing library in Go
Stars: ✭ 854 (+1756.52%)
DE-LIMITDeEpLearning models for MultIlingual haTespeech (DELIMIT): Benchmarking multilingual models across 9 languages and 16 datasets.
Stars: ✭ 90 (+95.65%)
Bert language understandingPre-training of Deep Bidirectional Transformers for Language Understanding: pre-train TextCNN
Stars: ✭ 933 (+1928.26%)
ParsBigBirdPersian Bert For Long-Range Sequences
Stars: ✭ 58 (+26.09%)
rasa milktea chatbotChatbot with bert chinese model, base on rasa framework(中文聊天机器人,结合bert意图分析,基于rasa框架)
Stars: ✭ 97 (+110.87%)
AiSpaceAiSpace: Better practices for deep learning model development and deployment For Tensorflow 2.0
Stars: ✭ 28 (-39.13%)
semantic-document-relationsImplementation, trained models and result data for the paper "Pairwise Multi-Class Document Classification for Semantic Relations between Wikipedia Articles"
Stars: ✭ 21 (-54.35%)
Awesome Qa😎 A curated list of the Question Answering (QA)
Stars: ✭ 596 (+1195.65%)
TapasEnd-to-end neural table-text understanding models.
Stars: ✭ 583 (+1167.39%)
denspiReal-Time Open-Domain Question Answering with Dense-Sparse Phrase Index (DenSPI)
Stars: ✭ 188 (+308.7%)
Chat基于自然语言理解与机器学习的聊天机器人,支持多用户并发及自定义多轮对话
Stars: ✭ 516 (+1021.74%)
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 (+304.35%)
Paper ReadingPaper reading list in natural language processing, including dialogue systems and text generation related topics.
Stars: ✭ 508 (+1004.35%)
Cdqa⛔ [NOT MAINTAINED] An End-To-End Closed Domain Question Answering System.
Stars: ✭ 500 (+986.96%)
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 (+656.52%)
Deep qaA deep NLP library, based on Keras / tf, focused on question answering (but useful for other NLP too)
Stars: ✭ 409 (+789.13%)
LMMSLanguage Modelling Makes Sense - WSD (and more) with Contextual Embeddings
Stars: ✭ 79 (+71.74%)
CogqaSource code and dataset for ACL 2019 paper "Cognitive Graph for Multi-Hop Reading Comprehension at Scale"
Stars: ✭ 399 (+767.39%)
FasterTransformerTransformer related optimization, including BERT, GPT
Stars: ✭ 1,571 (+3315.22%)
VideoBERTUsing VideoBERT to tackle video prediction
Stars: ✭ 56 (+21.74%)
Spm toolkitNeural network toolkit for sentence pair modeling.
Stars: ✭ 301 (+554.35%)
ganbertEnhancing the BERT training with Semi-supervised Generative Adversarial Networks
Stars: ✭ 205 (+345.65%)
Covid QaAPI & Webapp to answer questions about COVID-19. Using NLP (Question Answering) and trusted data sources.
Stars: ✭ 283 (+515.22%)
AnspressAnsPress is the most complete question and answer system for WordPress. AnsPress is made with developers in mind, highly customizable. AnsPress provide an easy to use override system for theme
Stars: ✭ 264 (+473.91%)
DiscEvalDiscourse Based Evaluation of Language Understanding
Stars: ✭ 18 (-60.87%)
Bert SquadSQuAD Question Answering Using BERT, PyTorch
Stars: ✭ 256 (+456.52%)
TOEFL-QAA question answering dataset for machine comprehension of spoken content
Stars: ✭ 61 (+32.61%)
squad-v1.1-ptPortuguese translation of the SQuAD dataset
Stars: ✭ 13 (-71.74%)
icebreakerWeb app that allows students to ask real-time, anonymous questions during class
Stars: ✭ 16 (-65.22%)
kwxBERT, LDA, and TFIDF based keyword extraction in Python
Stars: ✭ 33 (-28.26%)
HugsVisionHugsVision is a easy to use huggingface wrapper for state-of-the-art computer vision
Stars: ✭ 154 (+234.78%)
qaTensorFlow Models for the Stanford Question Answering Dataset
Stars: ✭ 72 (+56.52%)
berserkerBerserker - BERt chineSE woRd toKenizER
Stars: ✭ 17 (-63.04%)