Concordia University at the TREC 2007 QA Track.
Bibliographic record
Abstract
In this paper, we describe the system we used for the TREC Question Answering Track. For factoid and list questions two different approaches were exploited: A redundancy-based approach using a modified version of aranea and a parse-tree based unifier. The modified version of aranea essentially uses Google snippets for extracting answers and then projects them to aquaint. The parse-tree based unifier is a linguistic-based approach that chunks candidate sentences syntactically and uses a heuristic measure to compute the similarity of each chunk in a candidate to its counterpart in the question. To answer other types of questions, our system extracts from Wikipedia articles a list of interest-marking terms related to the topic and uses them to extract and score sentences from the aquaint document collection using various interest-marking triggers. We submitted 3 runs using different variations of the system. In the factoid run, the average of our 3 runs is 0.202, for the list, we achieved an average of 0.084, and for the “Other”, we achieved an average F-score of 0.192. 1
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 | 0.014 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.006 | 0.004 |
| Science and technology studies | 0.002 | 0.001 |
| Scholarly communication | 0.004 | 0.004 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.089 | 0.068 |
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".