ЛекториумМедиатека
Поиск
Личный кабинет

Character-level Convolutional Neural Network for Sentence Paraphrase Detection

This paper reports on the results of an experimental study on the application of characterlevel embeddings and basic convolutional neural network to the shared task of sentence paraphrase detection in Russian. The approach was tested in Task#2 standard run and offered competitive results (72.74% accuracy against the test set). This approach is compared against a word-level convolutional neural network for the same task.

Лекции курса

16
  1. Antiplagiat ResearchRita Kuznetsova
  2. A general method applicable to the search for anglicisms in russian social network textsIlia Karpov, Alena Fenogenova, Viktor Kazorin
  3. Deep learning tutorial. Part IAndrey Filchenkov
  4. Deep learning tutorial. Part IIСергей Николенко
  5. Character-level Convolutional Neural Network for Sentence Paraphrase Detection▶ Вы тут
  6. Combined Models for Russian Paraphrase Detection Shared TaskEkaterina Pronoza
  7. How to estimate user's real age and gender in social networkVitaly Khudobakhshov
  8. Neural nets for paraphrase detectionKirill Skornyakov
  9. HSE-School of linguistics at Russian Paraphrase Detection shared taskAnastasia Romanova, Mikhail Nefedov
  10. Lexical, Morphological and Semantic Correlates of the Dark Triad Personality Traits in Russian Facebook TextsЯнина Ледовая, Polina Panicheva, Olga Bogolyubova
  11. Morphosyntactic Tags in Statistical Machine Translation of Highly Inflectional LanguageMirjam S Maucec
  12. Multiword Expressions in Russian Thesauri RuThes and RuWordNetNatalia Loukachevitch
Показать все 16 лекций
  1. ParaPhraser: Russian Paraphrase Corpus and Shared TaskElena Yagunova
  2. Relational Machine Learning Author DisambiguationJose Millan, Ekaterina Bastrakova, Rodney Ledesma
  3. Semantic and Geospatial Mapping of Instagram Images in Saint-PetersburgОлеся Кольцова
  4. Topic Modeling for Frame Analysis of News MediaSergey Pashakhin

Онлайн-курсы по программированию

3