Context-Aware Translation Accuracy Improvement Strategies Based on Deep Reinforcement Learning in English Translation
Bibliographic record
Abstract
The field of machine translation has made significant progress in recent years, but how to improve translation accuracy and context consistency is still an urgent challenge.In this paper, a contextaware translation accuracy improvement strategy based on deep reinforcement learning is proposed for English translation.Based on CNNs neural machine translation model, the multi-intelligence deterministic deep policy gradient algorithm is utilized to combine the output of the translation model with the human evaluation index (BLEU), and the reward function is constructed to guide the model learning.In addition, in order to enhance the context-awareness of the model, the study introduces a context encoder in the deep reinforcement learning framework to capture sentencelevel contextual information and incorporate it into the translation process.The experimental results show that the optimized model has better training performance, with 40 epochs of iterations, the Loss converges to 0.135 up and down, and its English translation F1 value is 94.95%.And as the number of encoder layers rises, the number of semantic high-level features increases.The N-GRR difference between the generated translation and the standard translation of the model in this paper is the smallest, and the over-translation phenomenon is less.The number of out-of-set word interference is more than 6, and the BLEU value of this paper's model is improved by 17.89% to 55.55% compared with the comparison model.And the algorithm has good translation performance, with METEOR scores of 0.562~0.803on different topics.The research results fully verify the effectiveness of deep reinforcement learning based on deep reinforcement learning to improve the accuracy of English machine translation.
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.
How this classification was reachedexpand
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 | 0.002 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| 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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".