MétaCan
Menu
Back to cohort
Record W3023215888 · doi:10.18653/v1/2020.acl-main.142

TACRED Revisited: A Thorough Evaluation of the TACRED Relation Extraction Task

2020· preprint· en· W3023215888 on OpenAlexfundno aff
Christoph Alt, Aleksandra Gabryszak, Leonhard Hennig

Bibliographic record

Venuenot available
Typepreprint
Languageen
FieldComputer Science
TopicNatural Language Processing Techniques
Canadian institutionsnot available
FundersBundesministerium für Wirtschaft und EnergieBanting and Best Diabetes Centre, University of TorontoBundesministerium für Bildung und Forschung
KeywordsComputer scienceHeuristicsWord error rateTest setCeiling (cloud)Task (project management)Artificial intelligenceMachine learningCategorizationSet (abstract data type)Relation (database)Relationship extractionBaseline (sea)Test (biology)Natural language processingData mining

Abstract

fetched live from OpenAlex

TACRED (Zhang et al., 2017) is one of the largest, most widely used crowdsourced datasets in Relation Extraction (RE).But, even with recent advances in unsupervised pretraining and knowledge enhanced neural RE, models still show a high error rate.In this paper, we investigate the questions: Have we reached a performance ceiling or is there still room for improvement?And how do crowd annotations, dataset, and models contribute to this error rate?To answer these questions, we first validate the most challenging 5K examples in the development and test sets using trained annotators.We find that label errors account for 8% absolute F1 test error, and that more than 50% of the examples need to be relabeled.On the relabeled test set the average F1 score of a large baseline model set improves from 62.1 to 70.1.After validation, we analyze misclassifications on the challenging instances, categorize them into linguistically motivated error groups, and verify the resulting error hypotheses on three state-of-the-art RE models.We show that two groups of ambiguous relations are responsible for most of the remaining errors and that models may adopt shallow heuristics on the dataset when entities are not masked.

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)0.014
metaresearch head score (Gemma)0.030
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: Empirical
Teacher disagreement score0.015
Threshold uncertainty score0.075

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0140.030
Meta-epidemiology (narrow)0.0050.001
Meta-epidemiology (broad)0.0020.002
Bibliometrics0.0040.003
Science and technology studies0.0020.001
Scholarly communication0.0030.008
Open science0.0050.004
Research integrity0.0040.004
Insufficient payload (model declined to judge)0.0090.009

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 head0.053
GPT teacher head0.352
Teacher spread0.299 · 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

Citations9
Published2020
Admission routes1
Has abstractyes

Explore more

Same topicNatural Language Processing TechniquesFrench-language works237,207