A Multiplicative Model for Learning Distributed Text-Based Attribute\n Representations
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
In this paper we propose a general framework for learning distributed\nrepresentations of attributes: characteristics of text whose representations\ncan be jointly learned with word embeddings. Attributes can correspond to\ndocument indicators (to learn sentence vectors), language indicators (to learn\ndistributed language representations), meta-data and side information (such as\nthe age, gender and industry of a blogger) or representations of authors. We\ndescribe a third-order model where word context and attribute vectors interact\nmultiplicatively to predict the next word in a sequence. This leads to the\nnotion of conditional word similarity: how meanings of words change when\nconditioned on different attributes. We perform several experimental tasks\nincluding sentiment classification, cross-lingual document classification, and\nblog authorship attribution. We also qualitatively evaluate conditional word\nneighbours and attribute-conditioned text generation.\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 | 0.001 |
| 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 | 0.003 | 0.002 |
| 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