Overview of the TREC 2016 Contextual Suggestion Track
Bibliographic record
Abstract
The TREC Contextual Suggestion Track offers a personalized point of interest (POI) recommendation task, in which participants develop systems to give a ranked list of suggestions related to a profile and a context pair available in the tasks' requests provided by the track organizers. Previously, reusability of the contextual suggestion track suffered from using dynamic collections and a shallow pool depth. The main innovations at TREC 2016 are the following. First, the TREC CS web corpus, consisting of a web crawl of the TREC contextual suggestion collection, was made available. The rich textual descriptions of the web pages makes far more information available for each candidate POI in the collection. Second, we released endorsements (end user tags) of the attractions as given by NIST assessors, potentially matching the endorsements of POIs in another city as given by the person issuing the request as part of her profile. Third, a multi-depth pooling approach extending beyond the shallow top 5 pool was used. The multi-depth pooling approach has created a test collection that provides more reliable evaluation results in ranks deeper than the traditional pool cut-off.
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 | 0.018 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.002 |
| Bibliometrics | 0.011 | 0.011 |
| Science and technology studies | 0.004 | 0.001 |
| Scholarly communication | 0.004 | 0.006 |
| Open science | 0.003 | 0.003 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.023 | 0.024 |
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".