A oclusão pode facilitar a compreensão humana? Avaliação de explicabilidade no reconhecimento de entidades nomeadas
Bibliographic record
Abstract
Técnicas de Explicabilidade são métodos que auxiliam usuários a entender os resultados de um modelo de aprendizado de máquina. Nesse contexto, este trabalho investiga se a técnica de explicabilidade de Oclusão consegue gerar respostas similares às esperadas por humanos na classificação de palavras para o Reconhecimento de Entidades Nomeadas. Para isso, utilizou-se uma LSTM bidirecional e o conjunto de dados CoNLL 2003, bem como foi utilizado a anotação manual de 849 sentenças criando-se, assim, uma base de dados de referência. Os resultados mostram que a Oclusão é capaz de indicar pelo menos uma palavra relevante e compatível com a compreensão humana.
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 | 0.011 | 0.060 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.003 |
| Science and technology studies | 0.002 | 0.004 |
| Scholarly communication | 0.010 | 0.017 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.003 | 0.003 |
| Insufficient payload (model declined to judge) | 0.011 | 0.002 |
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".