watedu's starred repositories
ALBERT-BiLSTM-CRF-NER
Tensorflow 1.x solution for chinese NER task, using ALBERT-LSTM-CRF model
albert_ner
基于轻量级的albert实现albert+BiLstm+CRF
Attention-Based-BiLSTM-sentence-classify
Industry chain data test:Sentence classify Bi-GRU-att
structure_question_answer_system
基于bi-lstm-crf的实体抽取以及bi-gru-attention的实体关系识别,文本为数据结构课程, 来实现问答系统
Aspect-Sentiment-Classification
Code and models for the paper "Aspect Sentiment Classification with Aspect-Specific Opinion Spans", EMNLP 2020.
Review_Summarization-Aspect_based_opinion_mining
Summarize opinions of users about a product from a set of reviews. Extract the most common product features mentioned, most common opinion words used for a feature and the corresponding positive and negitive opinions about related to the feature and opinions. This way it becomes extremely easy to identify the most prominent positive and negitive features and opinions about a product.
Multi_Text_Classification
Multi Text Classificaiton
AppstoreGooglePlayReviewsTracker
Simple web app, which is tracking and reporting new reviews for apps in AppStore and Google Play
google-play-app-review-analysis
Topic detection and sentiment analysis of Google Play app reviews
multihead_joint_entity_relation_extraction
Implementation of our papers Joint entity recognition and relation extraction as a multi-head selection problem (Expert Syst. Appl, 2018) and Adversarial training for multi-context joint entity and relation extraction (EMNLP, 2018).
Result-Set-Visualization-d3js-R
Interactive Visualization Tree using D3JS; Here nodes can be dragged, zoomed and panned. It was designed to help developers to traverse through the huge result set of Text classifications using ML and Deep Learning approaches.
TextClassification-Keras
Text classification models implemented in Keras, including: FastText, TextCNN, TextRNN, TextBiRNN, TextAttBiRNN, HAN, RCNN, RCNNVariant, etc.
text-cnn-tensorflow
Convolutional Neural Networks for Sentence Classification(TextCNN) implements by TensorFlow
sentiment_analysis_textcnn
基于tensorflow 实现的用textcnn方法做情感分析的项目,有数据,可以直接跑。
ALBERT_4_Time_Recognition
使用ALBERT预训练模型,用于识别文本中的时间,同时验证模型的预测耗时是否有显著提升。
entity_extractor_by_pointer
使用torch整合两种经典的指针NER抽取范式,分别是SpanBert和苏神的GlobalPointer,简单加了些tricks,配置后一键运行
spo_extract_platform
本项目是利用深度学习技术来构建知识图谱方向上的一次尝试,作为开放领域的关系抽取,算是笔者的一次创新,目前在这方面的文章和项目都很少。
bilstm-crf
双向lstm+crf 序列标注
KBQA-for-Diagnosis
Knowledge Graph,Question Answering System,基于知识图谱和向量检索的医疗诊断问答系统
sequence_label
序列标注工具,可对文本进行多类别选中标注
bert_slot_tagging
用预训练BERT实现序列标注模型。