MétaCan
Menu
Back to cohort
Record W4225383538 · doi:10.32473/flairs.v35i.130643

Learning to Rank with BERT for Argument Quality Evaluation

2022· article· en· W4225383538 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.
fundA Canadian funder is recorded on the work.

Bibliographic record

VenueProceedings of the ... International Florida Artificial Intelligence Research Society Conference · 2022
Typearticle
Languageen
FieldComputer Science
TopicSoftware Engineering Research
Canadian institutionsPolytechnique Montréal
FundersSocial Sciences and Humanities Research Council of Canada
KeywordsArgument (complex analysis)Leverage (statistics)Ranking (information retrieval)Rank (graph theory)Computer scienceLearning to rankPairwise comparisonArtificial intelligenceQuality (philosophy)Machine learningRepresentation (politics)Task (project management)MathematicsEpistemologyPolitical scienceEngineering

Abstract

fetched live from OpenAlex

The task of argument quality ranking, which identifies the quality of free text arguments, remains, to this day, a challenge. While most state-of-the-art initiatives use point-wise ranking methods and predict an absolute quality score for each argument, we instead focus on learning how to order them by their relative convincingness, experimenting with several learning-to-rank methods for argument quality. We leverage BERT's powerful ability in building a representation of an argument, paired with learning-to-rank approaches (point-wise, pairwise, list-wise) to rank arguments according to their measure of convincingness. We also demonstrate how an ensemble of models trained with different ranking losses often improves the performance at identifying the most convincing arguments of a list. Finally, we compare BERT coupled with learning-to-rank methods to state-of-the-art approaches on all major argument quality datasets available for the ranking task, demonstrating how a learning-to-rank approach generally performs better at outlining the topmost convincing arguments.

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.

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)0.011
metaresearch head score (Gemma)0.005
Version: codex-gemma-dda1882f352aValidation 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: Empirical
Teacher disagreement score0.656
Threshold uncertainty score0.716

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0110.005
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0010.000
Scholarly communication0.0000.000
Open science0.0040.002
Research integrity0.0000.001
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 head0.173
GPT teacher head0.412
Teacher spread0.239 · 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