Neural Extractive Text Summarization with Syntactic Compression
This work addresses the problem of producing concise and grammatical summaries for natural language processing applications, but it is incremental as it builds on existing neural extraction and compression methods.
The authors tackled extractive text summarization by combining sentence selection with syntactic compression, achieving performance comparable to state-of-the-art systems on CNN/Daily Mail and New York Times datasets as measured by ROUGE scores.
Recent neural network approaches to summarization are largely either selection-based extraction or generation-based abstraction. In this work, we present a neural model for single-document summarization based on joint extraction and syntactic compression. Our model chooses sentences from the document, identifies possible compressions based on constituency parses, and scores those compressions with a neural model to produce the final summary. For learning, we construct oracle extractive-compressive summaries, then learn both of our components jointly with this supervision. Experimental results on the CNN/Daily Mail and New York Times datasets show that our model achieves strong performance (comparable to state-of-the-art systems) as evaluated by ROUGE. Moreover, our approach outperforms an off-the-shelf compression module, and human and manual evaluation shows that our model's output generally remains grammatical.