资源分类
》 资源 》论文》Latent Variable Sentiment Grammar?

Latent Variable Sentiment Grammar?

2019-09-22 | |  68 |   38 |   0 0 0
Abstract Neural models have been investigated for sentiment classification over constituent trees. They learn phrase composition automatically by encoding tree structures but do not explicitly model sentiment composition, which requires to encode sentiment class labels. To this end, we investigate two formalisms with deep sentiment representations that capture sentiment subtype expressions by latent variables and Gaussian mixture vectors, respectively. Experiments on Stanford Sentiment Treebank (SST) show the effectiveness of sentiment grammar over vanilla neural encoders. Using ELMo embeddings, our method gives the best results on this benchmark

上一篇：Label-Agnostic Sequence Labeling by Copying Nearest Neighbors

下一篇：Lightweight and Efficient Neural Natural Language Processing with Quaternion Networks

用户评价
全部评价

热门资源

  • The Variational S...

    Unlike traditional images which do not offer in...

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...

  • Rating-Boosted La...

    The performance of a recommendation system reli...