MétaCan
Menu
Back to cohort
Record W4388497942 · doi:10.1049/pbpc063e_ch8

Query-answering with text and knowledge graph

2023· book-chapter· en· W4388497942 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.

Bibliographic record

VenueInstitution of Engineering and Technology eBooks · 2023
Typebook-chapter
Languageen
FieldComputer Science
TopicSemantic Web and Ontologies
Canadian institutionsArtificial Intelligence in Medicine (Canada)
Fundersnot available
KeywordsComputer scienceSPARQLQuestion answeringInformation retrievalGraphQuery expansionQuery languageRepresentation (politics)Domain (mathematical analysis)Focus (optics)Web search querySimple (philosophy)RDFSemantic WebTheoretical computer scienceSearch engineMathematics

Abstract

fetched live from OpenAlex

Query-answering (QA) is one of the key areas in Artificial Intelligence, where various researches are performed in recent years. Building query-answering system helps the organization of all sectors. Generating automatic responses saves both time and money. We examine the problem of query-answering over knowledge graphs (KG) where various QA approaches focus on simpler queries and do not work very well for complex queries or vice versa. In addition to that, reasoning over KG is also to be handled properly to predict the proper answer to the corresponding query. Models that use SPARQL are good at domain-related queries, but they are unable to handle out-of-domain queries. Combining contextual text representation and semantic graph representation is a challenge. Our area of research is to combine text and KG for open domain query-answering. Adapting the joint representation ensures that the model can perform well in both simple and complex queries. In this chapter, we explain the various works that have been conducted and the challenges that have come along with it.

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: Theoretical or conceptual · Consensus signal: Theoretical or conceptual
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.922
Threshold uncertainty score0.766

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0010.000
Science and technology studies0.0000.000
Scholarly communication0.0000.000
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 head0.012
GPT teacher head0.199
Teacher spread0.187 · 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