A study on the application of graph convolutional network based joint model in entity relationship extraction
Bibliographic record
Abstract
Entity-relationship extraction task is one of the very important research directions in the field of natural language processing, aiming at identifying and determining the existence of specific relationships between entity pairs from unstructured text. The study firstly introduces the related theories of graph neural networks in terms of graph representation learning and graph neural networks, and then makes full use of the information of dependent syntactic trees to propose a relationship extraction model based on dependency graph convolution (DGGCN). The validity of the model and the entity extraction effect are verified through relevant experiments.The DGGCN model is fully experimented on the public datasets NYT and WebNLG, and the F1 value is effectively improved.According to the results of the ablation experiments, it is shown that the DGGCN model improves the entity and ternary extraction results by 0.5% and 4.3%, respectively. In the long and short distance entity extraction results, the DGGCN model outperforms the benchmark model in both long and short distance entity relations, but the extraction performance gap between short and long distance entity relations is still large and needs further improvement.
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 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.004 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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.
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".