Finding schwa: Comparing the results of an automatic aligner with human judgments when identifying schwa in a corpus of spoken French
Bibliographic record
Abstract
This paper compares the results of an automatic aligner with human judgments when identifying schwa in a natural language corpus of spoken French. All word-final, postconsonantal possible schwa insertion sites in the standardized text portion of investigations conducted in both Qu'ebec and France were both hand coded for schwa and time aligned at the word and phone level by the Penn Phonetics Lab Forced Aligner, modified for use with French. The results of the two methods of coding were statistically compared to determine their level of agreement. Preliminary results show a strong correlation between the two methods. Possible effects due to dialect or phonetic context were investigated using a two-way, between subjects analysis of variance. A mixed design analysis of variance was also conducted. Initial results have found no significant effect due to dialect, but a possible effect due to context. This suggests that the results of automatic alignment are comparable with human judgments in both dialects of French, but results may differ for individual speakers in specific contexts. The advantages of using an automatic aligner that can aid in the collection of larger volumes of natural language data than is possible when working manually is discussed.
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 | 0.045 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 0.002 |
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".