Understanding the effects of word-level linguistic annotations in under-resourced neural machine translation
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909087164268544 |
|---|---|
| author | Sánchez-Cartagena, Víctor M. Pérez-Ortiz, Juan Antonio Sánchez-Martínez, Felipe |
| author_facet | Sánchez-Cartagena, Víctor M. Pérez-Ortiz, Juan Antonio Sánchez-Martínez, Felipe |
| contents | This paper studies the effects of word-level linguistic annotations in under-resourced neural machine translation, for which there is incomplete evidence in the literature. The study covers eight language pairs, different training corpus sizes, two architectures, and three types of annotation: dummy tags (with no linguistic information at all), part-of-speech tags, and morpho-syntactic description tags, which consist of part of speech and morphological features. These linguistic annotations are interleaved in the input or output streams as a single tag placed before each word. In order to measure the performance under each scenario, we use automatic evaluation metrics and perform automatic error classification. Our experiments show that, in general, source-language annotations are helpful and morpho-syntactic descriptions outperform part of speech for some language pairs. On the contrary, when words are annotated in the target language, part-of-speech tags systematically outperform morpho-syntactic description tags in terms of automatic evaluation metrics, even though the use of morpho-syntactic description tags improves the grammaticality of the output. We provide a detailed analysis of the reasons behind this result. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_16078 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Understanding the effects of word-level linguistic annotations in under-resourced neural machine translation Sánchez-Cartagena, Víctor M. Pérez-Ortiz, Juan Antonio Sánchez-Martínez, Felipe Computation and Language This paper studies the effects of word-level linguistic annotations in under-resourced neural machine translation, for which there is incomplete evidence in the literature. The study covers eight language pairs, different training corpus sizes, two architectures, and three types of annotation: dummy tags (with no linguistic information at all), part-of-speech tags, and morpho-syntactic description tags, which consist of part of speech and morphological features. These linguistic annotations are interleaved in the input or output streams as a single tag placed before each word. In order to measure the performance under each scenario, we use automatic evaluation metrics and perform automatic error classification. Our experiments show that, in general, source-language annotations are helpful and morpho-syntactic descriptions outperform part of speech for some language pairs. On the contrary, when words are annotated in the target language, part-of-speech tags systematically outperform morpho-syntactic description tags in terms of automatic evaluation metrics, even though the use of morpho-syntactic description tags improves the grammaticality of the output. We provide a detailed analysis of the reasons behind this result. |
| title | Understanding the effects of word-level linguistic annotations in under-resourced neural machine translation |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2401.16078 |