#fasttext — Public Fediverse posts
Live and recent posts from across the Fediverse tagged #fasttext, aggregated by home.social.
-
I love Open Source. It frees you to fix issues and not just file bug reports and hope someone fixes the problem that is keeping you from being productive. I recently installed Eloquent proofreader from flathub to help with some tasks. Well it turns out that one of Eloquent's baked in dependencies fastText was an older version and was crashing on launch from the flatpak version of the app. But that did not stop me.
I did some searches and forked Eloquent on GitHub. I then also retrieved its two main dependencies, fastText and languagetool. I did not have to have a local languagetool, but I like working completely local when possible. So I built the three projects, put them together and installed them on my system. Which is a lot more solid than the flatpak version. I also now have a local languagetool to use with LibreOffice to boot 😉.
You do not get to have all this fun fixing your issues on proprietary systems. You just wait to see if anyone else will fix it for you. Which often just does not happen.
-
The #FastText paper: "Enriching Word Vectors with Subword Information", should've been called Word2Vec++, maybe...
-
The #FastText paper: "Enriching Word Vectors with Subword Information", should've been called Word2Vec++, maybe...
-
The #FastText paper: "Enriching Word Vectors with Subword Information", should've been called Word2Vec++, maybe...
-
The #FastText paper: "Enriching Word Vectors with Subword Information", should've been called Word2Vec++, maybe...
-
The #FastText paper: "Enriching Word Vectors with Subword Information", should've been called Word2Vec++, maybe...
-
เมื่อ FastText ยุติการพัฒนา การเขียนโค้ดเพื่อรันโมเดล FastText เลยยากกว่าเดิม แต่ก็ยังมีวิธีดึงโมเดลไปรันกับ numpy เพื่อใช้ get_sentence_vector ได้อยู่ สมกับเป็นตำนาน FastText จริง ๆ
#fasttext -
เมื่อ FastText ยุติการพัฒนา การเขียนโค้ดเพื่อรันโมเดล FastText เลยยากกว่าเดิม แต่ก็ยังมีวิธีดึงโมเดลไปรันกับ numpy เพื่อใช้ get_sentence_vector ได้อยู่ สมกับเป็นตำนาน FastText จริง ๆ
#fasttext -
เมื่อ FastText ยุติการพัฒนา การเขียนโค้ดเพื่อรันโมเดล FastText เลยยากกว่าเดิม แต่ก็ยังมีวิธีดึงโมเดลไปรันกับ numpy เพื่อใช้ get_sentence_vector ได้อยู่ สมกับเป็นตำนาน FastText จริง ๆ
#fasttext -
เมื่อ FastText ยุติการพัฒนา การเขียนโค้ดเพื่อรันโมเดล FastText เลยยากกว่าเดิม แต่ก็ยังมีวิธีดึงโมเดลไปรันกับ numpy เพื่อใช้ get_sentence_vector ได้อยู่ สมกับเป็นตำนาน FastText จริง ๆ
#fasttext -
We were not accepted into Google Summer of Code. So, we started our own
https://qdrant.tech/blog/qdrant-summer-of-code-24/
#ycombinator #vector_search_engine #neural_network #matching #SaaS #approximate_nearest_neighbor_search #image_search #recommender_system #vectors #knn_algorithm #hnsw #vector_search #embeddings #similarity #simaes_networks #BERT #transformer #word2vec #fasttext #qdrant -
We were not accepted into Google Summer of Code. So, we started our own
https://qdrant.tech/blog/qdrant-summer-of-code-24/
#ycombinator #vector_search_engine #neural_network #matching #SaaS #approximate_nearest_neighbor_search #image_search #recommender_system #vectors #knn_algorithm #hnsw #vector_search #embeddings #similarity #simaes_networks #BERT #transformer #word2vec #fasttext #qdrant -
We were not accepted into Google Summer of Code. So, we started our own
https://qdrant.tech/blog/qdrant-summer-of-code-24/
#ycombinator #vector_search_engine #neural_network #matching #SaaS #approximate_nearest_neighbor_search #image_search #recommender_system #vectors #knn_algorithm #hnsw #vector_search #embeddings #similarity #simaes_networks #BERT #transformer #word2vec #fasttext #qdrant -
We were not accepted into Google Summer of Code. So, we started our own
https://qdrant.tech/blog/qdrant-summer-of-code-24/
#ycombinator #vector_search_engine #neural_network #matching #SaaS #approximate_nearest_neighbor_search #image_search #recommender_system #vectors #knn_algorithm #hnsw #vector_search #embeddings #similarity #simaes_networks #BERT #transformer #word2vec #fasttext #qdrant -
Qdrant, the Vector Search Database, raised $28M in a Series A round
https://qdrant.tech/blog/series-a-funding-round/
#ycombinator #vector_search_engine #neural_network #matching #SaaS #approximate_nearest_neighbor_search #image_search #recommender_system #vectors #knn_algorithm #hnsw #vector_search #embeddings #similarity #simaes_networks #BERT #transformer #word2vec #fasttext #qdrant -
Qdrant, the Vector Search Database, raised $28M in a Series A round
https://qdrant.tech/blog/series-a-funding-round/
#ycombinator #vector_search_engine #neural_network #matching #SaaS #approximate_nearest_neighbor_search #image_search #recommender_system #vectors #knn_algorithm #hnsw #vector_search #embeddings #similarity #simaes_networks #BERT #transformer #word2vec #fasttext #qdrant -
Qdrant, the Vector Search Database, raised $28M in a Series A round
https://qdrant.tech/blog/series-a-funding-round/
#ycombinator #vector_search_engine #neural_network #matching #SaaS #approximate_nearest_neighbor_search #image_search #recommender_system #vectors #knn_algorithm #hnsw #vector_search #embeddings #similarity #simaes_networks #BERT #transformer #word2vec #fasttext #qdrant -
[Перевод] Краткий обзор техник векторизации в NLP
Как переводчик-редактор, я интересуюсь темой NLP и автоматизации рутины бюро переводов. Изучая вопрос того, как смысл слов превращается в векторы, наткнулся на эту обзорную статью. Статья мне показалась изложенной доступно, поэтому я перевел ее для удобства других коллег. Работоспособность большей части кода проверял, вроде работает (см. Jupiter Notebook). Надеюсь, будет полезно. === Технологии NLP — Natural Language Processing, обработки естественного языка — позволяют компьютерам обрабатывать человеческий язык, понимать его значение и контекст, а также связанные с ним эмоциональную окраску и намерения, и далее, использовать эти данные для создания чего-то нового. Как сделать слова понятными для компьютеров? Используется векторизация. Рассмотрим несколько техник такой векторизации.
https://habr.com/ru/articles/778048/
#токен #векторизация #fasttext #word2vec #glove #CBOW #skipgram #tfidf #nlp_(natural_language_processing)
-
[Перевод] Краткий обзор техник векторизации в NLP
Как переводчик-редактор, я интересуюсь темой NLP и автоматизации рутины бюро переводов. Изучая вопрос того, как смысл слов превращается в векторы, наткнулся на эту обзорную статью. Статья мне показалась изложенной доступно, поэтому я перевел ее для удобства других коллег. Работоспособность большей части кода проверял, вроде работает (см. Jupiter Notebook). Надеюсь, будет полезно. === Технологии NLP — Natural Language Processing, обработки естественного языка — позволяют компьютерам обрабатывать человеческий язык, понимать его значение и контекст, а также связанные с ним эмоциональную окраску и намерения, и далее, использовать эти данные для создания чего-то нового. Как сделать слова понятными для компьютеров? Используется векторизация. Рассмотрим несколько техник такой векторизации.
https://habr.com/ru/articles/778048/
#токен #векторизация #fasttext #word2vec #glove #CBOW #skipgram #tfidf #nlp_(natural_language_processing)
-
Even though this post is in German, the research article "Classification of Tragedies and Comedies in Calderón de la Barca’s Comedias Nuevas" has been published in English at https://zfdg.de/2022_012
We analyze 112 comedies of the Spanish Golden Age dramatist, explore 4 methods to classify them using #word #embeddings, compute #log #likelihood #probability, use #skipgram & #fasttext to characterize the corpus, and contrastive vocabulary analysis to characterize both genres
-
Even though this post is in German, the research article "Classification of Tragedies and Comedies in Calderón de la Barca’s Comedias Nuevas" has been published in English at https://zfdg.de/2022_012
We analyze 112 comedies of the Spanish Golden Age dramatist, explore 4 methods to classify them using #word #embeddings, compute #log #likelihood #probability, use #skipgram & #fasttext to characterize the corpus, and contrastive vocabulary analysis to characterize both genres
-
Even though this post is in German, the research article "Classification of Tragedies and Comedies in Calderón de la Barca’s Comedias Nuevas" has been published in English at https://zfdg.de/2022_012
We analyze 112 comedies of the Spanish Golden Age dramatist, explore 4 methods to classify them using #word #embeddings, compute #log #likelihood #probability, use #skipgram & #fasttext to characterize the corpus, and contrastive vocabulary analysis to characterize both genres
-
Even though this post is in German, the research article "Classification of Tragedies and Comedies in Calderón de la Barca’s Comedias Nuevas" has been published in English at https://zfdg.de/2022_012
We analyze 112 comedies of the Spanish Golden Age dramatist, explore 4 methods to classify them using #word #embeddings, compute #log #likelihood #probability, use #skipgram & #fasttext to characterize the corpus, and contrastive vocabulary analysis to characterize both genres
-
Even though this post is in German, the research article "Classification of Tragedies and Comedies in Calderón de la Barca’s Comedias Nuevas" has been published in English at https://zfdg.de/2022_012
We analyze 112 comedies of the Spanish Golden Age dramatist, explore 4 methods to classify them using #word #embeddings, compute #log #likelihood #probability, use #skipgram & #fasttext to characterize the corpus, and contrastive vocabulary analysis to characterize both genres
-
The research article "#Classification of Tragedies and Comedies in Calderón de la Barca’s Comedias Nuevas", written by @sebastianpado and me, has just been published:
https://revistas.uned.es/index.php/RHD/article/view/34588/
We analyze 112 comedies of the Spanish Golden Age dramatist and explore 4 methods to classify them into tragedies and comedies using #word #embeddings. We also employ the calculation of #log #likelihood #probability, #skipgram and #fasttext to characterize the corpus as well as ... -
The research article "#Classification of Tragedies and Comedies in Calderón de la Barca’s Comedias Nuevas", written by @sebastianpado and me, has just been published:
https://revistas.uned.es/index.php/RHD/article/view/34588/
We analyze 112 comedies of the Spanish Golden Age dramatist and explore 4 methods to classify them into tragedies and comedies using #word #embeddings. We also employ the calculation of #log #likelihood #probability, #skipgram and #fasttext to characterize the corpus as well as ... -
The research article "#Classification of Tragedies and Comedies in Calderón de la Barca’s Comedias Nuevas", written by @sebastianpado and me, has just been published:
https://revistas.uned.es/index.php/RHD/article/view/34588/
We analyze 112 comedies of the Spanish Golden Age dramatist and explore 4 methods to classify them into tragedies and comedies using #word #embeddings. We also employ the calculation of #log #likelihood #probability, #skipgram and #fasttext to characterize the corpus as well as ... -
The research article "#Classification of Tragedies and Comedies in Calderón de la Barca’s Comedias Nuevas", written by @sebastianpado and me, has just been published:
https://revistas.uned.es/index.php/RHD/article/view/34588/
We analyze 112 comedies of the Spanish Golden Age dramatist and explore 4 methods to classify them into tragedies and comedies using #word #embeddings. We also employ the calculation of #log #likelihood #probability, #skipgram and #fasttext to characterize the corpus as well as ...