MétaCan
Menu
Back to cohort
Record W3018695736 · doi:10.18653/v1/2020.acl-srw.16

Considering Likelihood in NLP Classification Explanations with Occlusion and Language Modeling

2020· preprint· en· W3018695736 on OpenAlexfundno aff
David Harbecke, Christoph Alt

Bibliographic record

Venuenot available
Typepreprint
Languageen
FieldComputer Science
TopicTopic Modeling
Canadian institutionsnot available
FundersBanting and Best Diabetes Centre, University of TorontoBundesministerium für Bildung und Forschung
KeywordsComputer scienceArtificial intelligenceNatural language processingLanguage modelContext (archaeology)Occlusion

Abstract

fetched live from OpenAlex

Recently, state-of-the-art NLP models gained an increasing syntactic and semantic understanding of language, and explanation methods are crucial to understand their decisions.Occlusion is a well established method that provides explanations on discrete language data, e.g. by removing a language unit from an input and measuring the impact on a model's decision.We argue that current occlusionbased methods often produce invalid or syntactically incorrect language data, neglecting the improved abilities of recent NLP models.Furthermore, gradient-based explanation methods disregard the discrete distribution of data in NLP.Thus, we propose OLM: a novel explanation method that combines occlusion and language models to sample valid and syntactically correct replacements with high likelihood, given the context of the original input.We lay out a theoretical foundation that alleviates these weaknesses of other explanation methods in NLP and provide results that underline the importance of considering data likelihood in occlusion-based explanation.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)0.012
metaresearch head score (Gemma)0.073
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: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.012
Threshold uncertainty score0.061

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0120.073
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0020.002
Bibliometrics0.0040.003
Science and technology studies0.0020.003
Scholarly communication0.0040.009
Open science0.0030.005
Research integrity0.0040.005
Insufficient payload (model declined to judge)0.0030.001

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 head0.054
GPT teacher head0.273
Teacher spread0.219 · 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

Citations2
Published2020
Admission routes1
Has abstractyes

Explore more

Same topicTopic ModelingFrench-language works237,207