MétaCan
Menu
← Back to cohort
Record W2900029582 · doi:10.22215/etd/2018-13317

Disregarding Linguistics: A Critical Study of Google Translate's Syntactic/Semantic Errors in Rendering Multiword Units in English to Persian Translations

2018· dissertation· en· W2900029582 on OpenAlexaff
Parnian Shafia

Bibliographic record

Venuenot available
Typedissertation
Languageen
FieldComputer Science
TopicNatural Language Processing Techniques
Canadian institutionsCarleton University
Fundersnot available
KeywordsComputer scienceNatural language processingMachine translationPersianArtificial intelligenceRendering (computer graphics)LinguisticsSource textCorpus linguisticsRule-based machine translation

Abstract

fetched live from OpenAlex

Translations rendered by machine translation have been found to be error-prone when translating medical communication language.Issues are especially frequent when Persian is either the source or target language.The source of errors has been attributed to machine translation's utilization of word-for-word translation and disregard for the formulaic nature of language.The aim of this research was, then, to investigate how multiword units (MWUs) of formulaic language (FL) are processed by a commonly used machine translator, Google Translate (GT).To do this, a medical-specific corpus was created to identify non-transparent MWUs.Adopting the framework by Simpson-Vlach and Ellis' (2010) n-gram criteria for MWUs, 20 frequently occurring MWUs were identified in the corpus.A comparison of GT's results with manual translations suggests that GT did not take FL into consideration in 50% of the data.These findings have implications for improving the accuracy of machine translation algorithms and reducing processing time.

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 imitation

Not 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.

metaresearch head score (Codex)0.013
metaresearch head score (Gemma)0.082
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.015
Threshold uncertainty score0.069

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0130.082
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0040.005
Science and technology studies0.0040.006
Scholarly communication0.0040.004
Open science0.0010.002
Research integrity0.0010.002
Insufficient payload (model declined to judge)0.0010.000

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.

Opus teacher head0.026
GPT teacher head0.342
Teacher spread0.317 · 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

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designObservational
Domainnot available
GenreEmpirical

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".

Quick stats

Citations0
Published2018
Admission routes1
Has abstractyes

Explore more

Same topicNatural Language Processing Techniques→French-language works237,207→