FBK Participation in the RTE-7 Main Task
Bibliographic record
Abstract
This paper overviews FBK’s participation in the RTE-7 Main task organized within the Text Analysis Conference (TAC) 2011. Our participation is characterized by two main themes, namely: 1. The attempt to move from token-level overlap measures (i.e. a count of the terms in the hypothesis that can be mapped to terms in the Text), to phraselevel overlap measures that take into account a larger context to favour system’s precision; 2. The attempt to use paraphrase tables derived from parallel data as the main source of lexical knowledge for the mapping. In contrast with previous experiments over different datasets on one side, and the scores achieved over the RTE-7 DEV SET on the other side, our final results are lower than those obtained with the simpler token-overlap algorithm (41.90% Vs 44.1% Micro-Averaged F-measure). The motivations for this unexpected performance drop are still under investigation.
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 | 0.028 | 0.037 |
| Meta-epidemiology (narrow) | 0.004 | 0.001 |
| Meta-epidemiology (broad) | 0.004 | 0.002 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.003 | 0.001 |
| Scholarly communication | 0.005 | 0.006 |
| Open science | 0.006 | 0.006 |
| Research integrity | 0.004 | 0.005 |
| Insufficient payload (model declined to judge) | 0.038 | 0.066 |
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".