Text summarization and text simplification are two major ways to simplify the text for poor readers, including children, non-native speakers, and the functionally illiterate. Text summarization is to produce a brief summary of the main ideas of th...
Current Chinese social media text summarization models are based on an encoder-decoder framework. Although its generated summaries are similar to source texts literally, they have low semantic relevance. In this work, our goal is to improve semant...
We propose a new recurrent neural CRF model for learning non-linear edge features. Our model is capable to completely encoding non-linear features for CRF. Experiments show that our model outperforms state-of-the-art methods in several structured ...
Credentials & highlights
- Project Views