Sosuke Kobayashi

bookcorpus. Crawl BookCorpus

attention_is_all_you_need. Transformer of "Attention Is All You Need" (Vaswani et al. 2017) by Chainer.

bert-chainer. Chainer implementation of "BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding"

dynamic_routing_between_capsules. Implementation of Dynamic Routing Between Capsules, Sara Sabour, Nicholas Frosst, Geoffrey E Hinton, NIPS 2017

convolutional_seq2seq. fairseq: Convolutional Sequence to Sequence Learning (Gehring et al. 2017) by Chainer

arxiv_leaks. Whisper of the arxiv: read comments in tex of papers

chainer-openai-transformer-lm. A Chainer implementation of OpenAI's finetuned transformer language model with a script to import the weights pre-trained by OpenAI

der-network. Dynamic Entity Representation (Kobayashi et al., 2016)

variational_dropout_sparsifies_dnn. Variational Dropout Sparsifies Deep Neural Networks (Molchanov et al. 2017) by Chainer

captioning_chainer. A fast implementation of Neural Image Caption by Chainer

ROCStory_skipthought_baseline. A novel baseline model for Story Cloze Test and ROCStories

efficient_softmax. BlackOut and Adaptive Softmax for language models by Chainer

dynamic_neural_text_model. A Neural Language Model for Dynamically Representing the Meanings of Unknown Words and Entities in a Discourse, Sosuke Kobayashi, Naoaki Okazaki, Kentaro Inui, IJCNLP 2017

interval-bound-propagation-chainer. Sven Gowal et al., Scalable Verified Training for Provably Robust Image Classification, ICCV 2019

learning_to_learn. Learning to learn by gradient descent by gradient descent, Andrychowicz et al., NIPS 2016

turnover_dropout. Python

weight_normalization. Weight Normalization (Salimans and Kingma, 2016) by Chainer

decode_from_mask. Generate a sentence from a masked sentence

SDCGAN. Sentence generation by DCGAN

elmo-chainer. Chainer implementation of contextualized word representations from bi-directional language models. Copied into https://github.com/chainer/models/tree/master/elmo-chainer

emergence_of_language_using_discrete_sequences. Emergence of Language Using Discrete Sequences

twitter_conversation_crawler. For crawling conversational tweet threads; e.g. datasets for chatbots.

vqvae_chainer. Chainer's Neural Discrete Representation Learning (Aaron van den Oord et al., 2017)

skip_thought. Language Model and Skip-Thought Vectors (Kiros et al. 2015)

sru_language_model. Language modeling experiments of SRU and variants

rnnlm_chainer. A Fast RNN Language Model by Chainer

DALL-E. PyTorch package for the discrete VAE used for DALL·E.

hyperreel. Code release for HyperReel High-Fidelity 3D Video with Ray-Conditioned Sampling