wangbq18

asr-tts-class-2021

ATLOP

Source code for paper "Document-Level Relation Extraction with Adaptive Thresholding and Localized Context Pooling".

bert4keras_document

bert4keras文档（非官方）

Biaffine-BERT-NER

A simple implementation of Biaffine NER.

BMGF-RoBERTa

Source Code for IJCAI 2020 paper "On the Importance of Word and Sentence Representation Learning in Implicit Discourse Relation Classification"

BoB

The source codes for ACL 2021 paper 'BoB: BERT Over BERT for Training Persona-based Dialogue Models from Limited Personalized Data'

casrel-ch

ccf_2020_qa_match

ccf 2020 qa match competition top1

ChineseNER

中文NER的那些事儿

CogLTX

CV_L_project

diting_audio

“谛听”声纹识别——基于Tensorflow架构深度学习声纹识别系统

DTLN

Tensorflow 2.x implementation of the DTLN real time speech denoising model. With TF-lite, ONNX and real-time audio processing support.

gaiic2021_track3_querySim

gaiic2021-track3-小布助手对话短文本语义匹配复赛rank3、决赛rank4

Guyu

pre-training and fine-tuning framework for text generation

HMNet-End-to-End-Abstractive-Summarization-for-Meetings

"End-to-End Abstractive Summarization for Meetings" paper - Unofficial PyTorch Implementation

JointIDSF

BERT-based joint intent detection and slot filling with intent-slot attention mechanism (INTERSPEECH 2021)

Keras_quasi_Mul_BERT

本项目使用Keras实现quasi Mul-BERT，在人物关系数据集上进行测试验证，其中quasi的意思为近似，因为Mul-BERT模型的论文还未发表，更多模型的细节还未知，因此为近似Mul-BERT。

keyword-transformer

mlm_bert_traning

基于mlm方式的带有纠错功能的拼音转汉字bert预训练模型，pinyin correcter，基于pytorch框架实现

NER-biaffine

NLP-model

NLP_Dialog_Response_Selection_MSN_BERT-ALBERT

Multi-hop Selector+BERT ,ALBERT 임베딩

soft-masked-bert-for-spelling-error-correction

A third-party implementation of paper《Spelling Error Correction with Soft-Masked BERT》using tensorflow==1.12.0

speech-denoising

Speech Denoising project for the Deep Learning course at Tsinghua University, spring 2021

TPlinker-joint-extraction

TPlinker-ycy

Tplinker注释，中文数据集适配版本

TripleExtraction

基于Biaffine Attention的三元组抽取模型，用于处理subject和object实体嵌套问题，且更方便处理相同关系多个object实体的情况

unif

Unified deep learning-based NLP framework that supports pretraining, text classification, text generation, NER, MRC, MT, and sequence labeling. Tensorflow1.x/2.x (≥1.11.0) is required.

wordwise

N-gram keyword extraction using transformers as zero-shot learners