MétaCan
Menu
Back to cohort
Record W6947722435 · doi:10.48448/axzg-7v02

One Wug, Two Wug+s Transformer Inflection Models Hallucinate Affixes

2022· other· en· W6947722435 on OpenAlex

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.

aboutThe title or abstract carries a Canadian signal from the geographic lexicon.
no affNo Canadian affiliation: this work is invisible to an affiliation-only frame.
No Canadian affiliation. An affiliation-only frame, the usual design, would never have seen this work. It is one of the works that make the case for inverting the frame.

Bibliographic record

VenueUnderline Science Inc. · 2022
Typeother
Languageen
FieldDecision Sciences
TopicData Quality and Management
Canadian institutionsnot available
Fundersnot available
KeywordsInflectionTransformerHallucinatingReduplicationHidden Markov modelFeature (linguistics)Pattern recognition (psychology)Inflection point

Abstract

fetched live from OpenAlex

Data augmentation strategies are increasingly important in NLP pipelines for low-resourced and endangered languages, and in neural morphological inflection, augmentation by so called data hallucination is a popular technique. This paper presents a detailed analysis of inflection models trained with and without data hallucination for the low-resourced Canadian Indigenous language Gitksan. Our analysis reveals evidence for a concatenative inductive bias in augmented models---in contrast to models trained without hallucination, they strongly prefer affixing inflection patterns over suppletive ones. We find that preference for affixation in general improves inflection performance in "wug test" like settings, where the model is asked to inflect lexemes missing from the training set. However, data hallucination dramatically reduces prediction accuracy for reduplicative forms due to a misanalysis of reduplication as affixation. While the overall impact of data hallucination for unseen lexemes remains positive, our findings call for greater qualitative analysis and more varied evaluation conditions in testing automatic inflection systems. Our results indicate that further innovations in data augmentation for computational morphology are desirable.

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 imitation

Not 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.

metaresearch head score (Codex)0.009
metaresearch head score (Gemma)0.001
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow), Insufficient payload (model declined to judge)
Consensus categoriesInsufficient payload (model declined to judge)
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Not applicable · Consensus signal: Not applicable
GenreCandidate signal: Other · Consensus signal: Other
Teacher disagreement score0.366
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0090.001
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0030.004
Science and technology studies0.0010.001
Scholarly communication0.0010.001
Open science0.0040.001
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0220.001

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.

Opus teacher head0.219
GPT teacher head0.426
Teacher spread0.207 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it