Lev Konstantinovskiy
where else to find them
what they talk about
where they keep going back
- PyData London3 editions2016–2018
on a stage with
never shared a talk
who talks about the same things
- Jesse Hall12 talks
- Rohit Gupta15 talks
- Elizabeth Fuentes Leone5 talks
- Ritesh Modi6 talks
- John Sandall6 talks
- Google DeepMind4 talks
| title | conference | date |
|---|---|---|
| Sentence embeddings for automated factchecking | PyData London 2018 | 2018-04-26 |
Uses InferSent sentence embeddings trained on SNLI with GloVe inputs and a BiLSTM max‑pool encoder to spot verifiable claims in political subtitles. Annotated… | ||
| Text similiarity with the next generation of word embeddings in Gensim | PyData Berlin 2017 | 2017-06-23 |
Shows concrete choices and outcomes: uses Gensim with Google's Word2vec, Facebook FastText, VarEmbed and WordRank; on a 120k‑word Pride and Prejudice corpus… | ||
| Next generation of word embeddings in Gensim | PyData London 2017 | 2017-05-05 |
Gensim presents concrete comparisons: fastText uses subword n‑grams so unseen forms like "knights" get plausible vectors and it outperforms on… | ||
| Word Embeddings for fun and profit in Gensim | PyData London 2016 | 2016-05-06 |
Uses Gensim to load Google News Word2Vec (300‑dim) and trains on 2,000 movie plots (170k words); builds document features by averaging word vectors and with… | ||
| nothing matches | ||