yuweiwan Goto Github PK

5-in-row

asr-hmm-dnn

speech recognition based on deep neural network/hidden markov model

asr-sg-hmm-gmm

speech recognition of digits based on single Gaussian, Gaussian Mixture, and Hidden Markov Models

bert-whitening-pytorch

Pytorch version of BERT-whitening

compare_mat_rank

fulltext_crawler

Fulltext paper download by api or crawling, together with processing (for Elsevier, Springer, RSC, etc. publishers)

golden-horse

Named Entity Recognition for Chinese social media (Weibo). From EMNLP 2015 paper.

graphmaster

Fully automated end to end framework to extract data from complex charts and other figures in scientific literature.

ii-ner

linguistics-work-sample

My undergraduate linguistics coursework and projects

mat2vec

Supplementary Materials for Tshitoyan et al. "Unsupervised word embeddings capture latent knowledge from materials science literature", Nature (2019).

ml-deep-learning

use pytorch to implement a two-layer NN and a convolutional NN

ml-dimension-reduction

PCA and LLE

ml-mrf

use Markov Random Field for image segmentation

ml-regression-tree

regression tree and gradient-boosted regression tree

my_notes

nlp-cfg

Design Context-Free Grammars and generate sentences

nlp-fsm

use OpenFST to explore Finite-State Programming

nlp-parsing

Parse sentence based on grammar.

nlp-spam-detection

train n-gram language model with different kinds of smoothing methods and detect spam emails

nlp-tagging

Use HMM to tag POS

nlp-word-embedding

embed words into vector space: can find similar words or similar relationship

nlper-interview

该仓库主要记录 NLP 算法工程师相关的面试题

nmtpoetry

novel_generation

paper-summary

sentence-transformers

Multilingual Sentence & Image Embeddings with BERT

summary_generation

text_classification

A text classification model

textmaster

Fully automated system to extract opinion from scientific literature in materials science and related fields.