MétaCan
Menu
Back to cohort

Measuring and Improving Faithfulness of Attention in Neural Machine Translation

2021· article· en· W3154790171 on OpenAlexafffund
Pooya Moradi, Nishant Kambhatla, Anoop Sarkar

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicTopic Modeling
Canadian institutionsSimon Fraser University
FundersNatural Sciences and Engineering Research Council of CanadaMinistère de la Défense Nationale
KeywordsMachine translationComputer scienceRegularization (linguistics)Measure (data warehouse)Artificial intelligenceTranslation (biology)Divergence (linguistics)Differentiable functionDeep neural networksQuality (philosophy)Machine learningArtificial neural networkNatural language processingMathematicsData miningLinguistics

Abstract

fetched live from OpenAlex

While the attention heatmaps produced by neural machine translation (NMT) models seem insightful, there is little evidence that they reflect a model's true internal reasoning.We provide a measure of faithfulness for NMT based on a variety of stress tests where attention weights which are crucial for prediction are perturbed and the model should alter its predictions if the learned weights are a faithful explanation of the predictions.We show that our proposed faithfulness measure for NMT models can be improved using a novel differentiable objective that rewards faithful behaviour by the model through probability divergence.Our experimental results on multiple language pairs show that our objective function is effective in increasing faithfulness and can lead to a useful analysis of NMT model behaviour and more trustworthy attention heatmaps.Our proposed objective improves faithfulness without reducing the translation quality and has a useful regularization effect on the NMT model and can even improve translation quality in some cases.

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)0.006
metaresearch head score (Gemma)0.038
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 score0.006
Threshold uncertainty score0.030

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0060.038
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0010.001
Science and technology studies0.0010.002
Scholarly communication0.0020.004
Open science0.0010.003
Research integrity0.0020.003
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 head0.044
GPT teacher head0.230
Teacher spread0.186 · 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

Citations14
Published2021
Admission routes2
Has abstractyes

Explore more

Same topicTopic ModelingFrench-language works237,207