Relation Mapping For Question Answering Over Knowledge Graphs Using Large Corpus Of Free Text
Bibliographic record
Abstract
With the advancements in semantic web technologies, researchers have developed several question answering systems that interpret the user's natural language question and fetches the answer from knowledge graphs.One of the main challenges of building question answering systems is determining which relations within a knowledge graph matches the keywords found in the Natural Language question.In order to bridge the gap between the simple yet ambiguous natural language question, and the difficult relation mapping problem, we propose ReMLOFT, an interactive relation mapping approach which relies on external evidence from a large corpus of text for mapping relations to the keywords found in a Natural Language question without using any training data.Our approach builds a free-text knowledge graph from Wikipedia, with entities as nodes and sentences in which these entities co-occur, as edges.ReMLOFT interactively helps the user choose better candidate relations to build fine-grained SPARQL queries.In addition, we build a dictionary of the most frequent keywords that define the context of a relation in the knowledge graph without using contemporary lexical tools.Experiments on three question answering datasets show our approach can map high quality candidate relations in comparison to statistical and embedding-based relation mapping approaches.
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 | 0.002 | 0.012 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.006 | 0.004 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.008 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.006 | 0.003 |
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".