Improving Semantic Relevance for Sequence-to-Sequence Learning of Chinese Social Media Text Summarization
This work addresses the issue of poor semantic alignment in summaries for Chinese social media users, but it is incremental as it builds on existing encoder-decoder frameworks.
The authors tackled the problem of low semantic relevance in Chinese social media text summarization by introducing a Semantic Relevance Based neural model that maximizes similarity between source text and summary representations, resulting in outperforming baseline systems on a social media corpus.
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 semantic relevance between source texts and summaries for Chinese social media summarization. We introduce a Semantic Relevance Based neural model to encourage high semantic similarity between texts and summaries. In our model, the source text is represented by a gated attention encoder, while the summary representation is produced by a decoder. Besides, the similarity score between the representations is maximized during training. Our experiments show that the proposed model outperforms baseline systems on a social media corpus.