karendeng
PhD in Engineering, Cambridge University || Supervised by Prof. Mark Gales
University of CambridgeCambridge, UK
Pinned Repositories
1-billion-word-language-modeling-benchmark
Formerly known as code.google.com/p/1-billion-word-language-modeling-benchmark
adaptive-softmax
Implements an efficient softmax approximation as described in the paper "Efficient softmax approximation for GPUs" (http://arxiv.org/abs/1609.04309)
alignment-viewer
A script that visualizes alignments between two sentences.
athena
an open-source implementation of sequence-to-sequence base speech processing engine
Auto-GPT
An experimental open-source attempt to make GPT-4 fully autonomous.
baselines-emnlp2016
This repository contains baseline models, training scripts, and instructions on how to reproduce our results for our state-of-art grammar correction system from M. Junczys-Dowmunt, R. Grundkiewicz: Phrase-based Machine Translation is State-of-the-Art for Automatic Grammatical Error Correction, EMNLP 2016.
brat
brat rapid annotation tool (brat) - for all your textual annotation needs
edit-extraction
Automatically extract grammatical edits from parallel original and corrected sentences.
imeasure
lectures
Oxford Deep NLP 2017 course
karendeng's Repositories
karendeng/adaptive-softmax
Implements an efficient softmax approximation as described in the paper "Efficient softmax approximation for GPUs" (http://arxiv.org/abs/1609.04309)
karendeng/athena
an open-source implementation of sequence-to-sequence base speech processing engine
karendeng/Auto-GPT
An experimental open-source attempt to make GPT-4 fully autonomous.
karendeng/caffe
Caffe: a fast open framework for deep learning.
karendeng/CoreNLP
Stanford CoreNLP: A Java suite of core NLP tools.
karendeng/DeepLearning-500-questions
深度学习500问,以问答形式对常用的概率知识、线性代数、机器学习、深度学习、计算机视觉等热点问题进行阐述,以帮助自己及有需要的读者。 全书分为18个章节,50余万字。由于水平有限,书中不妥之处恳请广大读者批评指正。 未完待续............ 如有意合作,联系scutjy2015@163.com 版权所有,违权必究 Tan 2018.06
karendeng/dynet
DyNet: The Dynamic Neural Network Toolkit
karendeng/gensim
Topic Modelling for Humans
karendeng/gtn
Automatic differentiation with weighted finite-state transducers.
karendeng/incubator-mxnet
Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Scala, Go, Javascript and more
karendeng/k2
FSA/FST algorithms, intended to (eventually) be interoperable with PyTorch and similar
karendeng/kaldi-dnn-ali-gop
Forced alignment and Goodness of Pronunciation (GOP) with DNN support. Bases on Kaldi.
karendeng/langchain
⚡ Building applications with LLMs through composability ⚡
karendeng/lattice_rnn
Bi-directional Lattice Recurrent Neural Networks for Confidence Estimation
karendeng/lhotse
karendeng/LightGBM
A fast, distributed, high performance gradient boosting (GBDT, GBRT, GBM or MART) framework based on decision tree algorithms, used for ranking, classification and many other machine learning tasks. It is under the umbrella of the DMTK(http://github.com/microsoft/dmtk) project of Microsoft.
karendeng/mlconvgec2018
Code and model files for the paper: "A Multilayer Convolutional Encoder-Decoder Neural Network for Grammatical Error Correction" (AAAI-18).
karendeng/models
Models built with TensorFlow
karendeng/mxnet-notebooks
Notebooks for MXNet
karendeng/nematus
Open-Source Neural Machine Translation in Theano
karendeng/OpenNMT
Open-Source Neural Machine Translation in Torch
karendeng/rnng
Recurrent neural network grammars
karendeng/smtgec2017
A statistical machine translation (SMT)-based grammatical error correction system that makes use of neural network joint models (NNJM) and and character-level SMT for spelling correction.
karendeng/snowfall
karendeng/spaCy
💫 Industrial-strength Natural Language Processing (NLP) with Python and Cython
karendeng/subword-nmt
Subword Neural Machine Translation
karendeng/tensorlayer
TensorLayer: Deep Learning and Reinforcement Learning Library for Researcher and Engineer.
karendeng/Theano
Theano is a Python library that allows you to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. It can use GPUs and perform efficient symbolic differentiation.
karendeng/vecmap
A framework to learn bilingual word embedding mappings
karendeng/vlcp
A production-ready SDN controller, and a highly-extensible SDN framework.