• A
  • A
  • A
  • ABC
  • ABC
  • ABC
  • А
  • А
  • А
  • А
  • А
Regular version of the site

Simplification of the Sentence: Computational and Experimental Approach

Student: Naumov Alexander

Supervisor: Olga Lyashevskaya

Faculty: Faculty of Humanities

Educational Programme: Fundamental and Computational Linguistics (Bachelor)

Year of Graduation: 2018

The automatic translation grows in popularity. And therefore the developers are looking for new ways to improve the algorithms and quality of their product. The workflow itself takes the sentence from one language and represents it in another. But, if the sentence is big and complex it becomes difficult to translate it correctly. So, simplification of the sentence will help to translate faster and more accurately. In this way, the main algorithm is to cut off optional words such as synonyms, repeating adjectives and etc. We will keep only the most important parts of the sentence. The simplification of the sentence is a very important aspect for machine translation. Especially it is very useful as a preprocessing step. In my diploma I will try to realize some algorithms of automatic and manual simplification and compare the results between each other in order to estimate the quality of the methode. The automatic simplification will be performed by special rules or using machine learning. And what is about manual, it will be made as experiment with speakers. The first goal is to make the algorithm for English language and to apply it for Russian language. In result, we have got quiet good results. All the experimental sentences were simplified with a quality.

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