An essential part of mastering a foreign language is measuring your proficiency level. With many tests present on the market, learners would like to find the one which would be fast and at the same time would cover all aspects of language. Python can help in building web services and also provides ways to integrate with different ML technologies to assess user’s proficiency level.
The task was to measure a person’s language proficiency level with a number, where the number is the highest item score the person is capable of answering correctly. This number should be reliable and correlated with TOEFL or CEFR scores. The product should be deployed Web-site capable of accepting large number of concurrent users.
We have managed to provide a fast and reliable Web service and clean and simple UI for language proficiency test which allows students to get their proficiency level within a few dozens of two-option questions. The results show a strong alignment between the test numbers and TOEFL scores.
We used Python, Django, MySQL on the backend side and AngularJS for UI. As an algorithm for computing the proficiency level we developed a Maximum Likelihood Estimation (MLE) and mode estimation models for solving this online regression task.
PCA
K-means
Decision trees
Linear models
PageRank
Digital filters
DTW
Deep learning
Probabilistic graphical models
CART
ensembles
unsupervised sound segmentation
recurrent models
bayesian approach
probabilistic programming
hmm
alexnet
vgg
vae
PCA
TF-IDF
LDA
SVM
Naive bayes
word2vec
attention models
Hi, we are Sciforce - a company where the integration of various branches of science builds up a powerful force to create robust software solutions. Working at the intersection of Computer Science with other technical, natural and humanitarian sciences let us go beyond traditional IT services and become both technical and scientific forces to our customers.