Towards Tailored Recovery of Lexical Diversity in Literary Machine Translation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914929828691968 |
|---|---|
| author | Ploeger, Esther Lai, Huiyuan van Noord, Rik Toral, Antonio |
| author_facet | Ploeger, Esther Lai, Huiyuan van Noord, Rik Toral, Antonio |
| contents | Machine translations are found to be lexically poorer than human translations. The loss of lexical diversity through MT poses an issue in the automatic translation of literature, where it matters not only what is written, but also how it is written. Current methods for increasing lexical diversity in MT are rigid. Yet, as we demonstrate, the degree of lexical diversity can vary considerably across different novels. Thus, rather than aiming for the rigid increase of lexical diversity, we reframe the task as recovering what is lost in the machine translation process. We propose a novel approach that consists of reranking translation candidates with a classifier that distinguishes between original and translated text. We evaluate our approach on 31 English-to-Dutch book translations, and find that, for certain books, our approach retrieves lexical diversity scores that are close to human translation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_17308 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Towards Tailored Recovery of Lexical Diversity in Literary Machine Translation Ploeger, Esther Lai, Huiyuan van Noord, Rik Toral, Antonio Computation and Language Machine translations are found to be lexically poorer than human translations. The loss of lexical diversity through MT poses an issue in the automatic translation of literature, where it matters not only what is written, but also how it is written. Current methods for increasing lexical diversity in MT are rigid. Yet, as we demonstrate, the degree of lexical diversity can vary considerably across different novels. Thus, rather than aiming for the rigid increase of lexical diversity, we reframe the task as recovering what is lost in the machine translation process. We propose a novel approach that consists of reranking translation candidates with a classifier that distinguishes between original and translated text. We evaluate our approach on 31 English-to-Dutch book translations, and find that, for certain books, our approach retrieves lexical diversity scores that are close to human translation. |
| title | Towards Tailored Recovery of Lexical Diversity in Literary Machine Translation |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2408.17308 |