Joohong Lee

Machine Learning Researcher

DiPair: Fast and Accurate Distillation for Trillion-Scale Text Matching and Pair Modeling (EMNLP 2020)

Poly-encoders: Transformer Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence Scoring (ICLR 2020)

ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators (ICLR 2020)

Adaptive Input Representations for Neural Language Modeling (ICLR 2019)

Generalization through Memorization: Nearest Neighbor Language Models (ICLR 2020)

Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks (EMNLP 2019)

Attentional Encoder Network for Targeted Sentiment Classification (arXiv 2019)

Aspect-based Sentiment Classification with Aspect-specific Graph Convolutional Networks (EMNLP 2019)

MoEL: Mixture of Empathetic Listeners (EMNLP 2019)

Gunrock: Building A Human-Like Social Bot By Leveraging Large Scale Real User Data (Alexa Prize 2018)

Rasa: Open Source Language Understanding and Dialogue Management (ConvAI 2017)

Towards Universal Dialogue State Tracking (EMNLP 2018)

The Design and Implementation of XiaoIce, an Empathetic Social Chatbot (arXiv 2018)

Recurrent Convolutional Neural Networks for Text Classification (AAAI 2015)

Character-Aware Neural Language Models (AAAI 2016)

FaceNet: A Unified Embedding for Face Recognition and Clustering (CVPR 2015)

Distant supervision for relation extraction without labeled data (ACL 2009)

Literature mining of host–pathogen interactions: comparing feature-based supervised learning and language-based approaches (Bioinformatics 2012)

Incorporating Relation Paths in Neural Relation Extraction (EMNLP 2017)

Relation Extraction with Multi-instance Multi-label Convolutional Neural Networks (COLING 2016)

Distant Supervision for Relation Extraction via Piecewise Convolutional Neural Networks (EMNLP 2015)

Relation Extraction: Perspective from Convolutional Neural Networks (NAACL 2015)

Relation Classification via Convolutional Deep Neural Network (COLING 2014)

Convolution Neural Network for Relation Extraction (ADMA 2013)