University of Amsterdam at the CLEF 2022 SimpleText Track
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
This paper reports on the University of Amsterdam’s participation in the CLEF 2022 SimpleText track. The overall goal of removing barriers that prevent the general public from accessing scientific literature is of great importance to help users make sense of a world of misinformation and shallow opinions. We perform preliminary studies within the track’s setup, analyzing the text complexity of searching a large set of academic abstracts in the context of popular science topics emerging in the news, with a specific focus at the relation between the topical relevance and the text complexity of the retrieved information. Our main findings are the following. First, we analyzed a large corpus of scientific abstracts and confirmed that these are highly complex on average, but that the variation is large and many abstracts with accessible readability levels exist. Second, we ran retrieval experiments and found that standard search ignores readability, yet filtering on the desirable reading level still retains competitive performance while avoiding retrieving relevant but incomprehensible results. Third, we ran complexity spotting experiments and found that straightforward lexical complexity or term frequency measures are strong indicators, but have to be combined with the importance of the concept in the broader context of the information request. Fourth, we ran a GPT-2 based text simplification model in a zero-shot way, resulting in conservative rewriting of abstracts, able to significantly reduce the text complexity. More generally, our results demonstrate that text complexity is an essential aspect to consider for improving non-expert access to scientific information, and opens up new routes to develop effective scientific information access technology tailored to needs of the general public.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
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 it