Research on Named Entity Recognition Method Based on Language Pre-Training Model
Bibliographic record
Abstract
Aiming at the problem that the existing named entity recognition models have insufficient ability to recognize common unknown words in data, this paper proposes a text vectorization representation method based on language pre-training model. The program can't understand the text directly, and it can only be understood by the program after the text is converted into a numerical value. Firstly, this paper introduces the methods of word vector representation, including discrete representation and distributed representation. The traditional word vector representation method can't deal with the problem of polysemy and can't fully express semantic features. Aiming at the defects of word vector method, this paper proposes a text vectorization method based on language pre-training model. The idea of fine-tune is introduced, and the pre-training model, which completed training on massive data sets, is transferred to the People's Daily data set, and the parameters are optimized. Finally, this paper designs a comparative experiment on the People's Daily data set, compares it with the traditional word embedding methods using CBOW, Skip-gram and GloVe, analyzes the results, and verifies the effectiveness of the proposed method.
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 | 0.001 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.007 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.003 | 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".