Developing module for transliterating search queries in online stores

Student: Davoian Albert

Supervisor: Anastasiya A. Bonch-Osmolovskaya

Educational Programme: Language Theory and Computational Linguistics (Master)

Final Grade: 10

Year of Graduation: 2017

The aim of the research is building a transliteration system for search query processing in the context of an online store. The paper covers main approaches to building machine transliteration systems and specifics of processing search queries. In order to resolve the task we built SMT based transliteration model and neural network based model. The model with best results was used to build a transliteration dictionary to integrate to the store's search engine. To evaluate the quality of the engine we used percentage of non-empty search results. SMT based model showed significant quality increase in comparison to other models.

Full text (added June 1, 2017)

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