Dependency Structure for News Document Summarization
This work addresses the problem of generating accurate summaries for news documents, which is incremental as it builds on existing methods by incorporating linguistic signals.
The authors tackled news document summarization by developing a neural network model that uses dependency parsing to capture cross-positional dependencies and grammatical structures, resulting in improved performance that outperforms existing works on a benchmark dataset.
In this work, we develop a neural network based model which leverages dependency parsing to capture cross-positional dependencies and grammatical structures. With the help of linguistic signals, sentence-level relations can be correctly captured, thus improving news documents summarization performance. Empirical studies demonstrate that this simple but effective method outperforms existing works on the benchmark dataset. Extensive analyses examine different settings and configurations of the proposed model which provide a good reference to the community.