Processing Natural Language Queries in Semantic WebApplications
Bibliographic record
Abstract
SPARQL is a powerful query language for an ever-growing number of Semantic Web applications.Using it, however, requires familiarity with the language which is not to be expected from the general web user.This drawback has led to the development of Question-Answering (QA) systems that enable users to express their information needs in natural language.This paper presents a novel dependency-based framework for translating natural language queries into SPARQL queries, which is based on the idea of syntactic parsing.The translation process involves the following five steps: extraction of the entities, extraction of the predicate, categorization of the query's type, resolution of lexical and semantic gaps between user query and domain ontology vocabularies; and construction of the SPARQL query.The proposed framework was tested on our closed-domain student advisory application intended to provide students with advice and recommendations about curriculum and scheduling matters.The advantage of our approach is that it requires neither any laborious feature engineering, nor complex model mapping of a query expressed in natural language to a SPARQL query template, and thus it can be easily adapted to a variety of domains.
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 imitationNot 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.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.006 | 0.013 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.003 | 0.003 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.004 | 0.007 |
| Open science | 0.002 | 0.004 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
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.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
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".