Analysis and Insights from the PARSEME Shared Task dataset
Bibliographic record
Abstract
The PARSEME Shared Task on the automatic identification of verbal multiword\nexpressions (VMWEs) was the first collaborative study on the subject to cover a\nwide and diverse range of languages. One observation that emerged from the official\nresults is that participating systems performed similarly on each language but\ndifferently across languages. That is, intra-language evaluation scores are relatively\nsimilar whereas inter-language scores are quite different. We hypothesise that this\npattern cannot be attributed solely to the intrinsic linguistic properties in each language\ncorpus, but also to more practical aspects such as the evaluation framework,\ncharacteristics of the test and training sets as well as metrics used for measuring\nperformance. This chapter takes a close look at the shared task dataset and the systems’\noutput to explain this pattern. In this process, we produce evaluation results\nfor the systems on VMWEs that only appear in the test set and contrast them with\nthe official evaluation results, which include VMWEs that also occur in the training\nset. Additionally, we conduct an analysis aimed at estimating the relative difficulty\nof VMWE detection for each language. This analysis consists of a) assessing the\nimpact on performance of the ability, or lack-thereof, of systems to handle discontinuous\nand overlapped VMWEs, b) measuring the relative sparsity of sentences\nwith at least one VMWE, and c) interpreting the performance of each system with\nrespect to two baseline systems: a system that simply tags every verb as a VMWE,\nand a dictionary lookup system. Based on our data analysis, we assess the suitability\nof the official evaluation methods, specifically the token-based method, and\npropose to use Cohen’s kappa score as an additional evaluation method.
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 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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, 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".