Bibliographic record
Abstract
We first present our work in machine translation, during which we used aligned sentences to train a neural network to embed n-grams of different languages into an d-dimensional space, such that n-grams that are the translation of each other are close with respect to some metric. Good n-grams to n-grams translation results were achieved, but full sentences translation is still problematic. We realized that learning semantics of sentences and documents was the key for solving a lot of natural language processing problems, and thus moved to the second part of our work: sentence compression. We introduce a flexible neural network architecture for learning embeddings of words and sentences that extract their semantics, propose an efficient implementation in the Torch framework and present embedding results comparable to the ones obtained with classical neural language models, while being more powerful. Acknowledgements First of all, I would like to thank NEC Labs for allowing me to come for six months to the United States and work on such an interesting project and in such an great environment. This was a wonderful experience, both on personal and professional levels. I met very interesting people at the lab, and had the opportunity to attend fascinating talks all along my project. I would also like to thank: Ronan Collobert, for his support in both my professional and personal life. He gave me great advice and feedback all along my project, and was always here when I needed support with the fantastic Torch framework he created. He also showed me some beautiful places in New Jersey and New York state, and even shared his love of Quebec during a great trip there. Jason Weston, for his help during the first part of my project. Prof. Martin Hasler, for accepting to supervise my Master Thesis from EPFL, taking the time to read my monthly reports and providing me with some helpful feedback. Contents
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 | 0.002 | 0.011 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.003 | 0.001 |
| Scholarly communication | 0.005 | 0.003 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.004 | 0.003 |
| Insufficient payload (model declined to judge) | 0.723 | 0.477 |
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; the direct Gemma label and the distilled Codex classifier agree on what is shown here.
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".