Neural Network-Based Abstract Generation for Opinions and Arguments
This work addresses the challenge of summarizing opinionated text for applications like review analysis or argument mining, representing an incremental improvement over existing methods.
The authors tackled the problem of generating abstractive summaries for opinionated text, such as movie reviews and arguments, by proposing an attention-based neural network model with importance-based sampling, which outperformed state-of-the-art systems in automatic evaluations and was rated more informative and grammatical in human evaluations.
We study the problem of generating abstractive summaries for opinionated text. We propose an attention-based neural network model that is able to absorb information from multiple text units to construct informative, concise, and fluent summaries. An importance-based sampling method is designed to allow the encoder to integrate information from an important subset of input. Automatic evaluation indicates that our system outperforms state-of-the-art abstractive and extractive summarization systems on two newly collected datasets of movie reviews and arguments. Our system summaries are also rated as more informative and grammatical in human evaluation.