Open-domain Question Answering System Development

Student: Golovina Mariia

Educational Programme: Financial Technology and Data Analysis (Master)

Year of Graduation: 2020

This paper describes development of an open-domain question-answering system. We used Google Natural Quesitons dataset and build a model inspired by BERT-joint. During experimenting stage we try out different BERT-based models such as Albert as a backbone for our model. We found out that adding XLNet trick to condition end tokens on start tokens of the answer span improves the results of the model. We also compare different ways of sampling the data for the training stage. Our final model is then served using Flask.

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