A multi-agent solution for managing complexity in english to sinhala machine translation
Bibliographic record
Abstract
Machine translation turns out to be an inherently complex process requiring serious attention to morphological, syntactic and semantic complexity within both the source and the target languages.Most of the existing approaches to machine translation (MT) circumvent the complexity with the assumption that morphological, syntactic and semantic analysis can be done independently and sequentially.This has resulted in depriving us of the opportunity to use the language complexity to generate high-quality translations.In view of this, research has been conducted to develop a multi-agent systems solution for MT that uses the language complexity as an opportunity for generating a more realistic translation from English to Sinhala.This multi-agent solution primarily comprises a six-agent swarm to deliberate on morphological, syntactic and semantic concerns of the source and the target languages without being constrained to operate in a sequential manner.These agents use the ontology of corpora and dictionary of two languages.This approach is inspired by the fact that people understand a sentence by incrementally reading through words while simultaneously considering the syntax and semantics.As such, when the system progresses in identification of words one by one, both syntactical and semantic concerns are entertained up to the current point of reading.As a result, initially decided words may be changed due to the present concern of morphology, syntax and semantics.A translation system has been implemented on the multi-agent system development framework named MaSMT.Experiments show that the multi-agent solution for MT gives promising results for translating sentences of an average length and further research has been carried out to accommodate translation of long sentences.
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.002 | 0.001 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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 source (direct Gemma or distilled Codex), 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".