University of Amsterdam at the CLEF 2024 Joker Track
Bibliographic record
Abstract
This paper reports on the University of Amsterdam’s participation in the CLEF 2024 Joker track. Our overall goal is to investigate non-literal use of language, such as in humor and wordplay, that are still challenging current information retrieval and natural language processing technology. Our specific focus is to investigate how an effective wordplay detector can be used for the humorous search results or candidate translations, within the context of the track’s humor retrieval, classification, and translation tasks. Our main findings are the following. First, standard ranking approaches are effective for retrieving relevant sentences given a query, but a pun classification filter is effective to select humorous results. Second, a BERT encoder based classifier obtains reasonable performance in classifying different aspects of humor, with some distinctions being hard for both models and humans. Third, sequence to sequences machine translation models provide high quality descriptive translation, yet preserving the wordplay across languages remains challenging. More generally, we revisited the CLEF 2023 Joker Track’s Pun Detection task, and were able to build effective neural pun classifiers. The value of these classifiers was demonstrated as a filter on the results of a standard ranker for the Humor-aware IR task of the CLEF 2024 Joker Track.
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 | 0.006 | 0.009 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.004 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.003 | 0.002 |
| Insufficient payload (model declined to judge) | 0.165 | 0.077 |
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".