Proceedings of the 19th Workshop on Multiword Expressions (MWE 2023)
Bibliographic record
Abstract
Lexical collocations: Explored a lot, still a lot more to explore Lexical collocations, i.e., idiosyncratic binary lexical item combinations, have been an active research topic already for a number of years.State-of-the-art neural network models report to detect and classify specific types of lexical collocations with high accuracy, which might suggest that the problem has been solved.However, a cross-type and cross-language analysis of the results of one of these models raises several relevant research questions.In the first part of my talk, I will present our recent work on the identification and classification of lexical collocations with respect to the fine-grained taxonomy of lexical functions (LFs) in English, French, Spanish and Japanese.Drawing on the outcome of this work, I will focus, in the second part of my talk, on the comparative analysis of the "LF profiles" of English and Japanese material.In particular, I will discuss (i) how the considered LFs are distributed in the given corpora; (ii) how rich the repertoires of the LF instances are in each of them; (iii) whether the contexts of the LF instances overlap; and (iv) to what extent the "profile" of an LF correlates with the accuracy of the recognition of its instances.To conclude, I will formulate the research questions that arise from this analysis.
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 | 0.004 | 0.008 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.002 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.006 | 0.010 |
| Open science | 0.003 | 0.005 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.155 | 0.084 |
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".