MétaCan
Menu
Back to cohort
Record W4402124327 · doi:10.1109/access.2024.3453215

A Comprehensive Evaluation of Neural SPARQL Query Generation From Natural Language Questions

2024· article· en· W4402124327 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

VenueIEEE Access · 2024
Typearticle
Languageen
FieldComputer Science
TopicTopic Modeling
Canadian institutionsPolytechnique Montréal
FundersNatural Sciences and Engineering Research Council of Canada
KeywordsComputer scienceSPARQLRDF query languageNatural language generationQuery languageNatural languageInformation retrievalNatural language processingWeb search queryArtificial intelligenceNatural language user interfaceWeb query classificationSearch engineSemantic WebRDF

Abstract

fetched live from OpenAlex

In recent years, the field of neural machine translation (NMT) for SPARQL query generation has witnessed significant growth. Incorporating the copy mechanism with traditional encoder-decoder architectures and using pre-trained encoder-decoder and large language models have set new performance benchmarks. This paper presents various experiments that replicate and expand upon recent NMT-based SPARQL generation studies, comparing pre-trained language models (PLMs), non-pre-trained language models (NPLMs), and large language models (LLMs), highlighting the impact of question annotation and the copy mechanism and testing various fine-tuning methods using LLMs. In particular, we provide a systematic error analysis of the models and test their generalization ability. Our study demonstrates that the copy mechanism yields significant performance enhancements for most PLMs and NPLMs. Annotating the data is pivotal to generating correct URIs, with the “tag-within” strategy emerging as the most effective approach. Additionally, our findings reveal that the primary source of errors stems from incorrect URIs in SPARQL queries that are sometimes replaced with hallucinated URIs when using base models. This does not happen using the copy mechanism, but it sometimes leads to selecting wrong URIs among candidates. Finally, the performance of the tested LLMs fell short of achieving the desired outcomes.

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)0.000
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: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.803
Threshold uncertainty score0.292

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 studies0.0000.000
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 head0.111
GPT teacher head0.385
Teacher spread0.275 · 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

Quick stats

Citations14
Published2024
Admission routes2
Has abstractyes

Explore more

Same venueIEEE AccessSame topicTopic ModelingFrench-language works237,207