A Study on the Linguistic Adaptation of Language Modeling Techniques in Translating British Victorian Literature
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
This paper discusses the application of the neural machine translation model based on language modeling technology in British Victorian literature and its linguistic adaptation.Firstly, the linguistic features of Victorian literary works are analyzed, including thematic content and social background.Then the neural machine translation model based on language modeling technology is designed, and the text style migration method based on style representation is proposed to reproduce the linguistic features of the literary works.The performance of the translation models under the three fusion style methods is compared with five baseline systems, and the BLEU value, style migration accuracy, and style migration fluency of the machine translation model using the text migration decoding module are 37.49, 0.978, and 3.59, respectively, which are all higher than those of other models.Taking the translation of Wuthering Heights as an example, there is not much difference between this model and the human translation in terms of language adaptation evaluation.It shows that the machine translation model designed based on language modeling technology in this paper has better language adaptability for translating Victorian literature.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.005 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it