MétaCan
Menu
Back to cohort
Record W2142669279 · doi:10.3115/v1/w14-3363

Linear Mixture Models for Robust Machine Translation

2014· article· en· W2142669279 on OpenAlexaff
Marine Carpuat, Cyril Goutte, George Foster

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicNatural Language Processing Techniques
Canadian institutionsNational Research Council Canada
Fundersnot available
KeywordsDomain adaptationComputer scienceMachine translationLeverage (statistics)Artificial intelligenceAdaptation (eye)Translation (biology)Machine learningDomain (mathematical analysis)RepurposingRobustness (evolution)Quality (philosophy)Linear modelHomogeneousMathematics

Abstract

fetched live from OpenAlex

As larger and more diverse parallel texts become available, how can we lever-age heterogeneous data to train robust machine translation systems that achieve good translation quality on various test domains? This challenge has been ad-dressed so far by repurposing techniques developed for domain adaptation, such as linear mixture models which combine estimates learned on homogeneous sub-domains. However, learning from large heterogeneous corpora is quite different from standard adaptation tasks with clear domain distinctions. In this paper, we show that linear mixture models can re-liably improve translation quality in very heterogeneous training conditions, even if the mixtures do not use any domain knowledge and attempt to learn generic models rather than adapt them to the tar-get domain. This surprising finding opens new perspectives for using mixture mod-els in machine translation beyond clear cut domain adaptation tasks. 1

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)0.004
metaresearch head score (Gemma)0.014
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.007
Threshold uncertainty score0.022

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0040.014
Meta-epidemiology (narrow)0.0020.002
Meta-epidemiology (broad)0.0020.002
Bibliometrics0.0020.003
Science and technology studies0.0010.002
Scholarly communication0.0020.003
Open science0.0020.003
Research integrity0.0030.004
Insufficient payload (model declined to judge)0.0050.005

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 head0.269
Teacher spread0.243 · 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 designSimulation or modeling
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

Citations6
Published2014
Admission routes1
Has abstractyes

Explore more

Same topicNatural Language Processing TechniquesFrench-language works237,207