• A
  • A
  • A
  • ABC
  • ABC
  • ABC
  • А
  • А
  • А
  • А
  • А
Regular version of the site
For visually-impairedUser profile (HSE staff only)SearchMenu

Predictive text for agglutinative and polysynthetic languages

Student: Sergey Kosyak

Supervisor: Francis M. Tyers

Faculty: Faculty of Humanities

Educational Programme: Computational Linguistics (Master)

Year of Graduation: 2021

This paper presents a set of experiments in the area of morphological modelling and predictioning. We examine the tasks of segmentation, next-unit prediction and predictive text entry for two under-resourced and indigenous languages, K'iche' and Chukchi. In segmentation we speak about different segmentation systems, four unsupervised and two supervised, and find the best morphological segmentation model. We then use it and statistical segmentation systems to make datasets for language modelling. We train models of different types - single-way segmented, which are trained using data from one segmentor, two-way segmented, which are trained using concatenated data from two segmentors, and finetuned, which are consistently trained on two datasets from different segmentors. We measure word and character level perplexities of the language models and find that the one trained on Wordpiece data and then finetuned on morphologically segmented data works the best. Given this we evaluate the models on a next-unit prediction task using the validation data, which was never used while model training. We find that Unigram model is the best for both languages at this task. Finally we test the language models on a task of predictive text entry using gold standard data and measure the average number of clicks per token and clicks per character. We find that the models trained using morphologically segmented data work well, although with substantial room for improvement. At last, we suppose that the usage of morphological segmentation will improve the end-user experience of predictive text usage and we plan testing this assumption, training other models and experimenting on more languages.

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