Query-Based Abstractive Summarization Using Neural Networks
This work addresses query-based summarization for text documents, but it is incremental as it adapts an existing model and dataset without major innovations.
The paper tackles query-based abstractive summarization by adapting an existing news dataset and training a pointer-generator neural network model, with results showing the model can use queries to produce targeted summaries as evaluated by similarity to references.
In this paper, we present a model for generating summaries of text documents with respect to a query. This is known as query-based summarization. We adapt an existing dataset of news article summaries for the task and train a pointer-generator model using this dataset. The generated summaries are evaluated by measuring similarity to reference summaries. Our results show that a neural network summarization model, similar to existing neural network models for abstractive summarization, can be constructed to make use of queries to produce targeted summaries.