4 3

Boris Orekhov

nevmenandr

https://nevmenandr.github.io/portfolio/

AI & ML interests

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

Recent Activity

posted an update about 12 hours 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 📜 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. 🎯 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. 🖼️ Visualization Attached is an infographic comparing the three models (architecture, style, generation sample). > RNNs aren't dead. They're just writing poetry in silence.

updated a dataset 8 months ago

nevmenandr/russian-20th-century-bigrams

updated a model 9 months ago

nevmenandr/w2v-russian-fiction

View all activity

Organizations

Posts 5

Post

https://huggingface.co/nevmenandr/char-based-lstm-russian-poetry-https://huggingface.co/nevmenandr/char-based-lstm-russian-poetry-mandelshtam
nevmenandr/char-based-lstm-russian-poetry-hexameter

Identifying the style by a qualified reader on a short fragment of generated poetry (2306.02771)

📜 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.

🎯 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.

🖼️ Visualization

Attached is an infographic comparing the three models (architecture, style, generation sample).

> RNNs aren't dead. They're just writing poetry in silence.

Post

2872

nevmenandr/w2v-chess

import gensim
from sklearn.decomposition import PCA
import matplotlib
import matplotlib.pyplot as plt

model = gensim.models.Word2Vec.load('white_moves.model')
dict_moves = model.wv.vocab
dict_moves_appr = {}
for k in dict_moves:
    if not k.startswith('->'):
        continue
    dict_moves_appr[k] = dict_moves[k]
X = model[model.wv.vocab]
pca = PCA(n_components=2)
result = pca.fit_transform(X)
fig, ax = plt.subplots()
ax.plot(Y[:, 0], Y[:, 1], 'o')
ax.set_title('White moves')
lab = list(dict_moves_appr)
for i, lb in enumerate(lab):
    plt.annotate(lb, xy=(Y[i, 0], Y[i, 1]))
plt.show()