Proceedings of TextGraphs-11: the Workshop on Graph-based Methods for Natural Language Processing
Bibliographic record
Abstract
Previous editions of TextGraphs have featured special themes, such as "Cognitive and Social Dynamics of Languages in the framework of Complex Networks" and "Large Scale Lexical Acquisition and Representation".For TextGraphs 2017, we set a special focus on the usage of graph-based methods to interpret deep learning models for NLP tasks.Though deep learning models have displayed state-ofthe-art performance on many NLP tasks, they are often criticized for not being interpretable (due to their various layers and large number of parameters).Through our theme, we hoped to spur a discussion on the development of methods for reasoning and interpretation of the layers used in deep learning models, given that a neural network is, from one point of view, nothing but a graph.We are pleased to have two excellent invited speakers for this year's event.We thank Apoorv Agarwal and
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 | 0.015 | 0.031 |
| Meta-epidemiology (narrow) | 0.003 | 0.002 |
| Meta-epidemiology (broad) | 0.004 | 0.004 |
| Bibliometrics | 0.007 | 0.006 |
| Science and technology studies | 0.002 | 0.003 |
| Scholarly communication | 0.009 | 0.012 |
| Open science | 0.005 | 0.006 |
| Research integrity | 0.004 | 0.007 |
| Insufficient payload (model declined to judge) | 0.023 | 0.009 |
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".