MétaCan
Menu
Back to cohort
Record W2740090399

The Challenge of Simultaneous Speech Translation

2016· article· en· W2740090399 on OpenAlexaff
Anoop Sarkar

Bibliographic record

VenueInstitutional Repositories DataBase (IRDB) · 2016
Typearticle
Languageen
FieldArts and Humanities
TopicTranslation Studies and Practices
Canadian institutionsSimon Fraser University
FundersTED
KeywordsComputer scienceSpeech translationTranslation (biology)Speech recognitionNatural language processingArtificial intelligenceMachine translationChemistry
DOInot available

Abstract

fetched live from OpenAlex

Simultaneous speech translation attempts to produce high quality translations while at the same time minimizing the latency between production of words in the source language and translation into the target language.The variation in syntactic structure between the source and target language can make this task challenging: translating from a language where the verb is at the end increases latency when translating incrementally into a language where the verb appears after the subject.In this talk I focus on a key prediction problem in simultaneous translation: when to start translating the input stream.I will talk about two new algorithms that together provide a solution to this problem.The first algorithm learns to find effective places to break the input stream.In order to balance the often conflicting demands of low latency and high translation quality, the algorithm exploits the notion of Pareto optimality.The second algorithm is a stream decoder that incrementally processes the input stream from left to right and produces output translations for segments of the input.These segments are found by consulting classifiers trained on data created by the first algorithm.

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 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)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Not applicable · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.996
Threshold uncertainty score0.871

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0010.001
Scholarly communication0.0000.001
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

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 head0.050
GPT teacher head0.274
Teacher spread0.224 · 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 teacher head, not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designNot applicable
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
Published2016
Admission routes1
Has abstractyes

Explore more

Same venueInstitutional Repositories DataBase (IRDB)Same topicTranslation Studies and PracticesFrench-language works237,207