Pinned Repositories
alone_old_seq2seq
alone_seq2seq
b2t_connection
control-length
fairseq
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
Frequency-Agnostic
Code for NIPS 2018 paper 'Frequency-Agnostic Word Representation'
GAC4relpat
Learning several composition functions (encoders) including Gated Additive Composition
relPatSim
relational pattern pairs with similarity ratings
rethink_perturbations
Rethinking Perturbations in Encoder-Decoders for Fast Training
share_layer_params
takase's Repositories
takase/control-length
takase/share_layer_params
takase/alone_seq2seq
takase/rethink_perturbations
Rethinking Perturbations in Encoder-Decoders for Fast Training
takase/relPatSim
relational pattern pairs with similarity ratings
takase/alone_old_seq2seq
takase/b2t_connection
takase/fairseq
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
takase/Frequency-Agnostic
Code for NIPS 2018 paper 'Frequency-Agnostic Word Representation'
takase/GAC4relpat
Learning several composition functions (encoders) including Gated Additive Composition
takase/lm-evaluation-harness
A framework for few-shot evaluation of autoregressive language models.
takase/mlpnlp-nmt
This is a sample code of "LSTM encoder-decoder with attention mechanism" mainly for understanding a recently developed machine translation framework based on deep neural networks.
takase/NAMAS
Neural Attention Model for Abstractive Summarization
takase/NLP-progress
Repository to track the progress in Natural Language Processing (NLP), including the datasets and the current state-of-the-art for the most common NLP tasks.
takase/paragram-word
Python code for training Paragram word embeddings. These achieve human-level performance on some word similiarty tasks including SimLex-999.This code was used to obtain results in the appendix of our 2015 TACL paper "From Paraphrase Database to Compositional Paraphrase Model and Back".
takase/takase.github.io
takase/tensor2tensor
Library of deep learning models and datasets designed to make deep learning more accessible and accelerate ML research.