Uncategorized

• Uncategorized

  • Learning Joint Multilingual Sentence Representations with Neural Machine Translation
  • A Corpus for Multilingual Document Classification in Eight Languages
  • Filtering and Mining Parallel Data in a Joint Multilingual Space
  • Margin-based Parallel Corpus Mining with Multilingual Sentence Embeddings
  • Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyond
  • Large vocabulary trick (LVT) - this reduces perplexity. But then you lose the capability to do "abstractive" summary. So they do "vocabulary expansion" by adding a layer of "word2vec nearest neighbors" to the words in the input.
  • Opinosis dataset
  • the public - based encoder-decoder method on it to generate summary. They took the whole short text as one sequence, this may not be very reasonable, because most of short texts contain several sentences.
  • Opinosis dataset