Name: Taeuk Kim
Type: User
Company: Hanyang University
Bio: Assistant Professor at Hanyang University.
B.S. & Ph.D. at Seoul National University.
Research Interests: NLP, Machine Learning, Deep Learning
Twitter: galsang1000
Location: Seoul, Korea.
Blog: https://galsang.github.io
Taeuk Kim's Projects
Implementation of ABCNN(Attention-Based Convolutional Neural Network) on Tensorflow
Re-implementation of Bi-Directional Block Self-Attention for Fast and Memory-Efficient Sequence Modeling (T. Shen et al., ICLR 2018) on Pytorch.
Re-implementation of BiDAF(Bidirectional Attention Flow for Machine Comprehension, Minjoon Seo et al., ICLR 2017) on PyTorch.
Re-implementation of BIMPM (Bilateral Multi-Perspective Matching for Natural Language Sentences, Zhiguo Wang et al.) on Pytorch.
Implementation of Convolutional Neural Networks for Sentence Classification (Y.Kim, EMNLP 2014) on Pytorch.
A tool for splitting and merging Korean unicode characters in Python 2 and 3
Korean Syllable Embedding implemented on AllenNLP
Subword-level Word Vector Representations for Korean (ACL 2018)
parser
Implementation of SATA Tree-LSTM (Dynamic Compositionality in Recursive Neural Networks with Structure-aware Tag Representations, AAAI 2019)
Implementation of SECOVARC (The Sentence Encoder with COntextualized Vectors for Argument Reasoning Comprehension), for SemEval-2018 Task 12 - The Argument Reasoning Comprehension Task.
Official Implementation for "Self-Gudied Contrastive Learning for BERT Sentence Representations (ACL 2021)"
Sent2Vec encoder and training code from the paper "Skip-Thought Vectors"
SNU_POI_web
Data loaders and abstractions for text and NLP
Official code for the ICLR 2020 paper 'ARE PPE-TRAINED LANGUAGE MODELS AWARE OF PHRASES? SIMPLE BUT STRONG BASELINES FOR GRAMMAR INDCUTION'.