Exploration of Language Translation Problems under the Background of Artificial Intelligence Technology
Bibliographic record
Abstract
With the deepening of globalized cooperation among countries around the world, the human society's demand for machine translation has increased rapidly, and the advancement of artificial intelligence technology has also put forward new requirements for the quality of machine translation.In this paper, we propose a neural machine translation model with adversarial training algorithm, using the Transformer model as the baseline model, by incorporating prior knowledge in order to strengthen the correlation between the intermediate hidden layers.In addition, besides introducing lexical knowledge into the neural machine translation approach, a neural machine translation model PhraseNet with phrase memory capable of storing bilingual phrases in the form of symbols is also incorporated.Finally, the effectiveness of the language translation model is tested using the NIST corpus.The results show that compared with the baseline model, the BLEU values of this paper's method in the NIST 2010, 2012, and 2016 test sets are improved by 1.81, 2.63, and 2.48, respectively, which significantly outperforms the baseline translation system.It shows that the method is able to bring a large improvement for both language translation accuracy and training execution cycle.Meanwhile, it also has a good guiding significance for the research and development of language translation in the context of the whole artificial intelligence technology.
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 | 0.001 | 0.000 |
| 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 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".