Arabic Poems Generation using LSTM, Markov-LSTM and Pre-Trained GPT-2 Models
Bibliographic record
Abstract
Nowadays, artificial intelligence applications are increasingly integrated into every aspect of our lives. One of the newest applications in artificial intelligence and natural language is text generation, which has received considerable attention in recent years due to the advancements in deep learning and language modeling techniques. Text generation has been investigated in different domains to generate essays and books. Writing poetry is a highly complex intellectual process for humans that requires creativity and high linguistic capability. Several researchers have examined automatic poem generation using deep learning techniques, but only a few attempts have looked into Arabic poetry. Attempts to evaluate the generated pomes coherence in terms of meaning and themes still require further investigation. In this paper, we examined character-based LSTM, Markov-LSTM, and pre-trained GPT-2 models in generating Arabic praise poems. The results of all models were evaluated using BLEU scores and human evaluation. The results of both BLEU scores and human evaluation show that the Markov-LSTM has outperformed both LSTM and GPT-2, where the character-based LSTM model gave the lowest yields in terms of meaning due to its tendency to create unknown words.
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 | 0.000 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| 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".