Development of a System Generating Sequences of Machine Learning Pipelines Meta-Descriptions Based on Natural Language

Student: Levin Alexander

Supervisor: Andrey Ustyuzhanin

Faculty: International laboratory for Applied Network Research

Educational Programme: Applied Statistics with Network Analysis (Master)

Year of Graduation: 2021

There were major breakthroughs in the area of source code generation, such as source code generative models and datasets. But still, there are gaps like the generation of machine learning code specifically. The basis of source code generation complexity is in the lack of special datasets: source code corpora. In this project, a domain representation "Machine Learning Knowledge Graph", a source code corpus "Machine Learning Code Corpus" parsed from Kaggle, and a generative "task2seq" model generating machine learning pipelines based on a vector of the competition features. This source code corpus allows to build various machine learning models for source code analysis, such as source code classifiers or source code generators in the future.

Student Theses at HSE must be completed in accordance with the University Rules and regulations specified by each educational programme.

Summaries of all theses must be published and made freely available on the HSE website.

The full text of a thesis can be published in open access on the HSE website only if the authoring student (copyright holder) agrees, or, if the thesis was written by a team of students, if all the co-authors (copyright holders) agree. After a thesis is published on the HSE website, it obtains the status of an online publication.

Student theses are objects of copyright and their use is subject to limitations in accordance with the Russian Federation’s law on intellectual property.

In the event that a thesis is quoted or otherwise used, reference to the author’s name and the source of quotation is required.

Search all student theses