A Correlational Encoder Decoder Architecture for Pivot Based Sequence\n Generation
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
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.
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) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 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 it