A Correlational Encoder Decoder Architecture for Pivot Based Sequence\n Generation
Bibliographic record
Abstract
Interlingua based Machine Translation (MT) aims to encode multiple languages\ninto a common linguistic representation and then decode sentences in multiple\ntarget languages from this representation. In this work we explore this idea in\nthe context of neural encoder decoder architectures, albeit on a smaller scale\nand without MT as the end goal. Specifically, we consider the case of three\nlanguages or modalities X, Z and Y wherein we are interested in generating\nsequences in Y starting from information available in X. However, there is no\nparallel training data available between X and Y but, training data is\navailable between X & Z and Z & Y (as is often the case in many real world\napplications). Z thus acts as a pivot/bridge. An obvious solution, which is\nperhaps less elegant but works very well in practice is to train a two stage\nmodel which first converts from X to Z and then from Z to Y. Instead we explore\nan interlingua inspired solution which jointly learns to do the following (i)\nencode X and Z to a common representation and (ii) decode Y from this common\nrepresentation. We evaluate our model on two tasks: (i) bridge transliteration\nand (ii) bridge captioning. We report promising results in both these\napplications and believe that this is a right step towards truly interlingua\ninspired encoder decoder architectures.\n
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.007 | 0.003 |
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".