A fuzzy model for NMT word alignment using quasi-perfect matching
In this article, first, the concept of quasi-perfect matching in a fuzzy graph is introduced. In addition to using these types of matching in expressing our main application goal, this introduction provides a complete classification on all matching that are known as “maximum matching” in classical g...
Saved in:
| Published in: | Computational & applied mathematics Vol. 42; no. 8 |
|---|---|
| Main Authors: | , , |
| Format: | Journal Article |
| Language: | English |
| Published: |
Cham
Springer International Publishing
01-12-2023
Springer Nature B.V |
| Subjects: | |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | In this article, first, the concept of quasi-perfect matching in a fuzzy graph is introduced. In addition to using these types of matching in expressing our main application goal, this introduction provides a complete classification on all matching that are known as “maximum matching” in classical graph theory. A useful set called conductive set has been obtained to be able to customize any of the introduced categories for matchings as desired or according to the practical necessity. Extensions with different powers are made from a fuzzy graph and useful meters are generated on each of them. These extensions and related concepts have been used in a different approach for words alignment in machine translation. The mismatch between the number of sentence words in the source and target languages has always been a challenge for the designers of machine translation systems in word-based alignment. To solve this, we introduce a different approach for aligning words, based on a fuzzy graph extracted from a parallel corpus. |
|---|---|
| ISSN: | 2238-3603 1807-0302 |
| DOI: | 10.1007/s40314-023-02498-1 |