Jason Hao's Blog

Jason Hao's Blog
0%

Posted on In , Views: Valine: 1.5k 1 mins.

Entity Recognition A related blog with interpretion of these papers HERE

A related code implementations of these papers HERE

  • A Survey on Deep Learning for Named Entity Recognition(2018) [paper]

  • A Survey on Recent Advances in Named Entity Recognition from Deep Learning models(2018)[paper]

  • BLSTM+CRF Bidirectional LSTM-CRF Models for Sequence Tagging(2015) [paper]

  • Char+BLSTM+CRF Attending to Characters in Neural Sequence Labeling Models(2016)[paper]

  • BLSTM+CNN Named Entity Recognition with Bidirectional LSTM-CNNs (2016) [paper]

  • Char+Radical Character-Based LSTM-CRF with Radical-Level Features for Chinese Named Entity Recognition(2016)[paper]

  • BLSTM+CRF Neural Architectures for Named Entity Recognition (2016) [paper]

  • BLSTM+CNN+CRF End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF(2016) [paper]

  • FOFE A FOFE-based Local Detection Approach for Named Entity Recognition and Mention Detection(2016)[paper]

  • IDCNN Fast and Accurate Entity Recognition with Iterated Dilated Convolutions(2017) [paper]

  • DAL Deep Active Learning for Named Entity Recognition(2017)[paper]

  • Neural Architectures for Fine-grained Entity Type Classification (2017)[paper]

  • TagLM Semi-supervised sequence tagging with bidirectional language models(2017)[paper]

  • LatticeNER Chinese NER Using Lattice LSTM(2018)[paper]

  • AutoNER Learning Named Entity Tagger using Domain-Specific Dictionary(2018)[paper]

  • ATLNER Adversarial Transfer Learning for Chinese Named Entity Recognition with Self-Attention Mechanism(2018)[paper]

  • ALCrowd Adversarial Learning for Chinese NER from Crowd Annotations(2018)[paper]

  • ACN Adaptive Co-Attention Network for Named Entity Recognition in Tweets(2018)[paper]

References

Kaiyuang Gao's github

Posted on In , Views: Valine: 3.2k 3 mins.

Relation Classification and Extraction

A related blog with interpretion of these papers HERE

A related code implementations of these papers HERE

  • NLP-progress in Relation Extraction

  • Relation Extraction : A Survey(2017)[paper]

  • DSRE Distant supervision for relation extraction without labeled data(2009) [paper]

  • CNN Convolution Neural Network for Relation Extraction(2013)[paper]

  • CNN Relation Classification via Convolutional Deep Neural Network(2014)[paper]

  • CR-CNN Classifying Relations by Ranking with Convolutional Neural Networks(2015)[paper]

  • RNN Relation Classification via Recurrent Neural Network(2015)[paper]

  • CNN Relation Extraction: Perspective from Convolutional Neural Networks(2015)[paper]

  • PCNN Distant Supervision for Relation Extraction via Piecewise Convolutional Neural Networks(2015)[paper]

  • SATT Neural Relation Extraction with Selective Attention over Instances(2016)[paper]

  • MIMLCNN Relation Extraction with Multi-instance Multi-label Convolutional Neural Networks(2016)[paper]

  • MLACNN Relation Classification via Multi-Level Attention CNNs(2016)[paper]

  • BILSTM Bidirectional Long Short-Term Memory Networks for Relation Classification(2016)[paper]

  • TRLSTM End-to-End Relation Extraction using LSTMs on Sequences and Tree Structure(2016)[paper]

  • ABLSTM Attention-Based Bidirectional Long Short-Term Memory Networks for Relation Classification(2016)[paper]

  • HRNN+ATT Semantic Relation Classification via Hierarchical Recurrent Neural Network with Attention(2016) [paper]

  • CoType CoType: Joint Extraction of Typed Entities and Relations with Knowledge Bases(2016)[paper]

  • Weakly-supervised Relation Extraction by Pattern-enhanced Embedding Learning(2016)[paper]

  • BRCNN Bidirectional Recurrent Convolutional Neural Network for Relation Classification(2016) [paper]

  • APCNN Distant Supervision for Relation Extraction with Sentence-Level Attention and Entity Descriptions(2017)[paper]

  • CNN MIT at SemEval-2017 Task 10: Relation Extraction with Convolutional Neural Networks(2017)[paper]

  • MNRE Neural Relation Extraction with Multi-lingual Attention(2017)[paper]

  • DRCNN Deep Residual Learning for Weakly-Supervised Relation Extraction(2017)[paper]

  • Learning with Noise: Enhance Distantly Supervised Relation Extraction with Dynamic Transition Matrix(2017)[paper]

  • Joint Extraction of Entities and Relations Based on a Novel Tagging Scheme(2017)[paper]

  • Joint Entity and Relation Extraction Based on A Hybrid Neural Network(2017)[paper]

  • Extracting Entities and Relations with Joint Minimum Risk Training(2018)[paper]

  • Effectively Combining Recurrent and Convolutional Neural Networks for Relation Classification and Extraction(2018)[paper]

  • Joint Extraction of Entities and Relations Based on a Novel Graph Scheme(2018)[paper]

  • Ranking-Based Automatic Seed Selection and Noise Reduction for Weakly Supervised Relation Extraction(2018)[paper]

  • Hierarchical Relation Extraction with Coarse-to-Fine Grained Attention(2018)[paper]

  • RESIDE: Improving Distantly-Supervised Neural Relation Extraction using Side Information(2018)[paper]

  • A Walk-based Model on Entity Graphs for Relation Extraction(2018)[paper]

  • FewRel: A Large-Scale Supervised Few-Shot Relation Classification Dataset with State-of-the-Art Evaluation(2018)[paper]

  • Semantic Relation Classification via Bidirectional LSTM Networks with Entity-aware Attention using Latent Entity Typing (2019)[paper]

  • Large Scaled Relation Extraction with Reinforcement Learning(2018)[paper]

  • Robust Distant Supervision Relation Extraction via Deep Reinforcement Learning(2018)[[paper]]

  • Reinforcement Learning for Relation Classification from Noisy Data(2018)[paper]

References

  1. KaiyuanGao's Github

Posted on Edited on In Views: Valine: 501 1 mins.

  1. all walks of life 各行各业: we have witnessed a wide spread of artificial intelligence technologies to all walks of life.

  2. time-consuming, error-prone, and the maintenance is laborious

  3. mean, refer to, reflect, suggest

  4. coarse-grained or fine-grained

  5. describe, portray

  6. retained candidates 保留下来的 candidates

  7. unwanted words, stop words, stop-list words

  8. an agreed/ shared definition

  9. a cascade of: 一连串的 modern hybrid systems are usually composed by a cascade of a first linguistic analysis.

  10. unceasingly: Many applications extended from ontology have been brought up unceasingly (不停地)

References