Upgrade to Pro — share decks privately, control downloads, hide ads and more …

diora

Zhang Yixiao
February 10, 2020
240

 diora

Zhang Yixiao

February 10, 2020
Tweet

Transcript

  1. Introduction • 模型建立在latent tree chart parser的现有工作上。 • - Semi-supervised recursive

    autoencoders for predicting sentiment distributions • - The forest convolutional network: Compositional distributional semantics with a neural chart and without binarization • - Learning to compose task-specific tree structures, AAAI 2018 • - Jointly Learning Sentence Embeddings and Syntax with Unsupervised Tree-LSTMs • CKY算法也是一种chart parser。
  2. Experiment • 模型在三个task上应用: • Unsupervised Parsing • Phrase Segmentation •

    看模型识别出了句子中有多少个短语 • Phrase Similarity • 首先用DIORA算出每个短语的表示,然后两两短语之间算cos相似 度,对于一个短语,如果与它最相似的K个短语的label和它一样, 那么这个短语就预测对了。
  3. 相关论文 • Semi-supervised recursive autoencoders for predicting sentiment distributions •

    The forest convolutional network: Compositional distributional semantics with a neural chart and without binarization • Learning to compose task-specific tree structures, AAAI 2018 • Jointly Learning Sentence Embeddings and Syntax with Unsupervised Tree-LSTMs • Do latent tree learning models identify meaningful structure in sentences? • Grammar induction with neural language models: An unusual replication • Structured alignment networks for matching sentences • graph-based dependency parser + beam search: The insideoutside recursive neural network model for dependency parsing • Neural crf parsing