Deep Learning, NLP, NMT, AI, ML
PyTorch implementation of Attentive Recurrent Comparators by Shyam et al. A blog explaining Attentive Recurrent Comparators Visualizing Attention On Same characters On Different Characters How to run? Download data A one-time 52MB download. Shouldn’t take more than a few minutes. Train Let it train until the accuracy rises to at least 80%. Early stopping is not implemented yet. You will have to manually kill the process.
Read more
Pytorch implementation of “Attention-Based Recurrent Neural Network Models for Joint Intent Detection and Slot Filling” (https://arxiv.org/pdf/1609.01454.pdf) Intent prediction and slot filling are performed in two branches based on Encoder-Decoder model. dataset (Atis) You can get data from here Requirements Train python3 train.py –data_path ‘your data path e.g. ./data/atis-2.train.w-intent.iob’ Result GitHub https://github.com/DSKSD/RNN-for-Joint-NLU
Read more
News SRU++, a new SRU variant, is released. [tech report] [blog] The experimental code and SRU++ implementation are available on the dev branch which will be merged into master later. About SRU is a recurrent unit that can run over 10 times faster than cuDNN LSTM, without loss of accuracy tested on many tasks. Average processing time of LSTM, conv2d and SRU, tested on GTX 1070 For example, the figure above presents the processing time of a single mini-batch of […]
Read more
Dancing to Music PyTorch implementation of the cross-modality generative model that synthesizes dance from music. Paper Hsin-Ying Lee, Xiaodong Yang, Ming-Yu Liu, Ting-Chun Wang, Yu-Ding Lu, Ming-Hsuan Yang, Jan KautzDancing to Music Neural Information Processing Systems (NeurIPS) 2019[Paper] [YouTube] [Project] [Blog] [Supp] Example Videos Beat-Matching1st row: generated dance sequences, 2nd row: music beats, 3rd row: kinematics beats MultimodalityGenerate various dance sequences with
Read more
A Virtual Desktop Assistant Written in Python. It’s generally a basic virtual assistant The basic purpose of this is to make work easier as it re-directs you to various main sites and performs various important functions for your PC as well just install it for your system and run it in your code editor or IDE. I will be soon updating it as an application for MacOS, Linux and Windows. Until then you can follow the Contributing Guidelines and Contribute […]
Read more
With the semester start, it is also time to renew MT Weekly. My new year’s resolution was to make it to 100 issues, so let’s see if I can keep it. Today, I will talk about a paper by my colleagues from LMU Munich that will appear in the Findings of EMNLP 2021 which deals with a perpetual problem of NLP – input text segmentation. The title of the paper is Wine is Not v i n. On the Compatibility […]
Read more