Hierarchical Neural Networks for Sequential Sentence Classification in Medical Scientific Abstracts
arXiv:1808.06161
Abstract
Prevalent models based on artificial neural network (ANN) for sentence classification often classify sentences in isolation without considering the context in which sentences appear. This hampers the traditional sentence classification approaches to the problem of sequential sentence classification, where structured prediction is needed for better overall classification performance. In this work, we present a hierarchical sequential labeling network to make use of the contextual information within surrounding sentences to help classify the current sentence. Our model outperforms the state-of-the-art results by 2%-3% on two benchmarking datasets for sequential sentence classification in medical scientific abstracts.
arXiv commentAccepted by EMNLP 2018
References in corpus (9)
- Adam: A Method for Stochastic Optimization
- Convolutional Neural Networks for Sentence Classification
- Recurrent Neural Network for Text Classification with Multi-Task Learning
- Enriching Word Vectors with Subword Information
- Dependency-based Convolutional Neural Networks for Sentence Embedding
- PubMed 200k RCT: a Dataset for Sequential Sentence Classification in Medical Abstracts
- Dropout with Expectation-linear Regularization
- Dependency Sensitive Convolutional Neural Networks for Modeling Sentences and Documents
- Neural Networks for Joint Sentence Classification in Medical Paper Abstracts