MétaCan
Menu
Back to cohort
Record W2954097401 · doi:10.7152/acro.v29i1.15455

Machine translation and author keywords: A viable search strategy for scholars with limited English proficiency?

2019· article· en· W2954097401 on OpenAlexaff
Lynne Bowker

Bibliographic record

VenueAdvances in Classification Research Online · 2019
Typearticle
Languageen
FieldComputer Science
TopicNatural Language Processing Techniques
Canadian institutionsUniversity of Ottawa
Fundersnot available
KeywordsComputer scienceSearch engine indexingInformation retrievalMachine translationDomain (mathematical analysis)Field (mathematics)Natural language processingArtificial intelligenceVariation (astronomy)

Abstract

fetched live from OpenAlex

Author keywords are valuable for indexing articles and for information retrieval (IR). Most scientific literature is published in English. Can machine translation (MT) help researchers with limited English proficiency to search for information? We used two MT systems (Google Translate, DeepL Translator) to translate into English 71 Spanish keywords and 43 French keywords from articles in the domain of Library and Information Science. We then used the English translations to search the Library, Information Science and Technology Abstracts (LISTA) database. Half of the translated keywords returned relevant results. Of the half that did not, 34% were well translated but did not align with LISTA descriptors. Translation-related problems stemming from orthographic variation, synonymy, differing syntactic preferences, and semantic field coverage interfered with IR in just 16% of cases. Some of the MT errors are relatively “predictable” and if knowledge organization systems could be augmented to deal with them, then MT may prove even more useful for searching.

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)0.007
metaresearch head score (Gemma)0.041
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesMetaresearch, Scholarly communication
Consensus categoriesnone
DomainCandidate signal: Methods · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.995
Threshold uncertainty score0.066

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0070.041
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0020.001
Bibliometrics0.0090.010
Science and technology studies0.0010.001
Scholarly communication0.0050.010
Open science0.0010.003
Research integrity0.0020.001
Insufficient payload (model declined to judge)0.0200.016

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 head0.105
GPT teacher head0.433
Teacher spread0.328 · 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.

Study designObservational
DomainMethods
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

Citations17
Published2019
Admission routes1
Has abstractyes

Explore more

Same venueAdvances in Classification Research OnlineSame topicNatural Language Processing TechniquesFrench-language works237,207