Hugging Face's logo
Boris Orekhov's picture
4 3

Boris Orekhov

nevmenandr
webxos's profile picture codemurt's profile picture izaitova's profile picture
Ā·
https://nevmenandr.github.io/portfolio/

AI & ML interests

Natural Language Processing, Poetry Generation, Linguistics, Low-resource languages

Recent Activity

posted an update 2 days ago
https://huggingface.co/nevmenandr/char-based-lstm-russian-poetry-pasternak šŸ§  LSTM Language Model Visualization: A Deep Dive into Char-RNN šŸ“Š Model Architecture at a Glance - Model Type: 5-layer LSTM - Hidden Size: 512 - Vocabulary: 137 characters - Sequence Length: 50 - Total Parameters: ~9.8 million - Training: 50 epochs, 10,750 iterations - Final Validation Loss: 1.1266 - The model learned to generate Pasternak-style poetry - pretty impressive for a char-rnn! šŸŽØ The Beautiful Mess Check out this heatmap visualization - it's like a Persian carpet! šŸ āœØ - Each gate has its own patterns: - Input Gate: Controls what new info enters the cell - Forget Gate: Decides what to discard - Cell Gate: Creates new candidate values - Output Gate: Determines what to output - The weights show beautiful structured patterns - different gates learned distinct strategies for processing text.https://huggingface.co/papers/2306.02771
posted an update 12 days ago
šŸ”„ New Russian Stylometry Dataset! Russian Stylometric Dataset (RSD) ā€” 322 texts from the 19th ā€“ early 20th centuries (16 million words), prepared for analysis in stylo (R) and machine learning (Python). šŸ“š What's inside? Fiction, journalism, scientific texts, drama, poetry Grouped by author, gender, age, genre, literary movements (Romanticism/Realism) Character speech (Tolstoy, Gogol, Ostrovsky) Generated texts (LSTM, GPT) šŸ“Š Use cases: authorship attribution, clustering, classification, benchmarking methods. šŸ”“ Public domain + GPL-3.0 license. šŸ‘‰ Learn more: https://github.com/nevmenandr/RSD DOI: 10.5281/zenodo.20701309
posted an update 14 days ago
https://huggingface.co/nevmenandr/char-based-lstm-russian-poetry-https://huggingface.co/nevmenandr/char-based-lstm-russian-poetry-mandelshtam https://huggingface.co/nevmenandr/char-based-lstm-russian-poetry-hexameter https://huggingface.co/papers/2306.02771 šŸ“œ RNN vs. Transformers: How an Old Architecture Better Perceives Poetic Style In the era of Transformer dominance, we often forget that old RNNs (especially character-level LSTMs) remain irreplaceable for tasks where *individual style*, rhythm, and micro-patterns matter. These three models are clear proof of that. šŸŽÆ Why does this matter today? - **Stylistic analysis**: RNNs better capture meter, repetitions, and unexpected tonal shifts. - **Teaching poetics**: generating "almost correct" but hallucinating lines helps explore the boundaries of style. - **Nostalgia and replication**: a reminder that not everything is measured by BLEU and perplexity. šŸ–¼ļø Visualization Attached is an infographic comparing the three models (architecture, style, generation sample). > RNNs aren't dead. They're just writing poetry in silence.
View all activity

Organizations

HSE University's profile picture DH CLOUD's profile picture