Korean jamo-level byte-pair encoding for neural machine translation
Tokenization is the very first step in most Natural Language Processing tasks, and is essential in addressing the fundamental out-of-vocabulary problem, as well as in changing the linguistic understanding. To exploit the characteristics of the Korean language for a more parameter-efficient tokenizat...
Saved in:
Main Author: | |
---|---|
Other Authors: | |
Format: | Final Year Project |
Language: | English |
Published: |
Nanyang Technological University
2023
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/172737 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
Summary: | Tokenization is the very first step in most Natural Language Processing tasks, and is essential in addressing the fundamental out-of-vocabulary problem, as well as in changing the linguistic understanding. To exploit the characteristics of the Korean language for a more parameter-efficient tokenization strategy in Neural Machine Translation pipeline, this project considers the compositional nature of Korean syllables. An alphabet-level tokenization is introduced in combination with Byte-Pair Encoding, together with a mitigation strategy to address potential invalidities in the generated sequence. Experimental results demonstrate that the proposed tokenization method show improvements in both BLEU and chrF compared to syllable-based baselines in English-to-Korean translation task.
The codebase for this project is available on https://github.com/jylee-k/joeynmt/tree/ token masking. |
---|