| Title: | On the use of morpho-syntactic description tags in neural machine translation with small and large training corpora |
|---|
| Authors: | ID Donaj, Gregor (Author)
ID Sepesy Maučec, Mirjam (Author) |
|---|
| Files: |  mathematics-10-01608-v2.pdf (448,16 KB)
MD5: 72D7F80C90A379F904D01A7DC8D27267
 https://www.mdpi.com/2227-7390/10/9/1608
|
|---|
| Language: | English |
|---|
| Work type: | Article |
|---|
| Typology: | 1.01 - Original Scientific Article |
|---|
| Organization: | FERI - Faculty of Electrical Engineering and Computer Science
|
|---|
| Abstract: | With the transition to neural architectures, machine translation achieves very good quality for several resource-rich languages. However, the results are still much worse for languages
with complex morphology, especially if they are low-resource languages. This paper reports the
results of a systematic analysis of adding morphological information into neural machine translation
system training. Translation systems presented and compared in this research exploit morphological
information from corpora in different formats. Some formats join semantic and grammatical information and others separate these two types of information. Semantic information is modeled using
lemmas and grammatical information using Morpho-Syntactic Description (MSD) tags. Experiments
were performed on corpora of different sizes for the English–Slovene language pair. The conclusions
were drawn for a domain-specific translation system and for a translation system for the general
domain. With MSD tags, we improved the performance by up to 1.40 and 1.68 BLEU points in the
two translation directions. We found that systems with training corpora in different formats improve
the performance differently depending on the translation direction and corpora size. |
|---|
| Keywords: | neural machine translation, POS tags, MSD tags, inflected language, data sparsity, corpora size |
|---|
| Publication status: | Published |
|---|
| Publication version: | Version of Record |
|---|
| Submitted for review: | 31.01.2022 |
|---|
| Article acceptance date: | 06.05.2022 |
|---|
| Publication date: | 09.05.2022 |
|---|
| Publisher: | MDPI AG |
|---|
| Year of publishing: | 2022 |
|---|
| Number of pages: | 21 str. |
|---|
| Numbering: | Vol. 10, no. 9 |
|---|
| PID: | 20.500.12556/DKUM-92312  |
|---|
| UDC: | 004.5 |
|---|
| ISSN on article: | 2227-7390 |
|---|
| COBISS.SI-ID: | 107195395 |
|---|
| DOI: | 10.3390/math10091608 |
|---|
| Copyright: | © 2022 by the authors |
|---|
| Publication date in DKUM: | 28.03.2025 |
|---|
| Views: | 153 |
|---|
| Downloads: | 16 |
|---|
| Metadata: |    |
|---|
| Categories: | Misc.
|
|---|
|
:
|
Copy citation |
|---|
| | | | Average score: | (0 votes) |
|---|
| Your score: | Voting is allowed only for logged in users. |
|---|
| Share: |  |
|---|
Hover the mouse pointer over a document title to show the abstract or click
on the title to get all document metadata. |
