takase Goto Github PK

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

lm-evaluation-harness

A framework for few-shot evaluation of autoregressive language models.

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.

namas

Neural Attention Model for Abstractive Summarization

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.

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".

relpatsim

relational pattern pairs with similarity ratings

rethink_perturbations

Rethinking Perturbations in Encoder-Decoders for Fast Training

share_layer_params

takase.github.io

tensor2tensor

Library of deep learning models and datasets designed to make deep learning more accessible and accelerate ML research.