Annotated Suffix Tree Method for German Compound Splitting

Student: Shishkova Anna

Supervisor: Ekaterina Artemova

Educational Programme: Applied Mathematics and Information Science (Bachelor)

Year of Graduation: 2016

The paper presents an application of annotated suffix tree (AST) method to German compound. A compound word is a word consisting of several independent parts, e.g. Bordkarte (boarding pass) is a combination of two words: Bord and Karte. We use the AST method to determine the longest and sufficiently frequent suffix, i.e. the word’s substring ending with its last letter, and to perform a candidate split based on this suffix. We successively modify the base algorithm to achieve competitive results with 95% precision. Test results on compound word lists and German texts suggest the method is apt for natural language processing. For instance, the method can be used to facilitate foreign language learning or to determine the linguistic style of a text. An open-source, web-based implementation of the algorithm is presented.

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