Query-Based Abstractive Summarization Using Neural Networks

Johan Hasselqvist, Niklas Helmertz, Mikael Kågebäck
12/17/2017
cs.CL

Official code: helmertz/querysum (14 stars, last commit 2017-06-09). 1 more implementation below.

Abstract

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.

View on arXivView PDF

Code Implementations(2)

helmertz/querysumOfficial100%
145PythonJun 7, 20179 years ago
helmertz/querysum-dataOfficial100%
103PythonJun 7, 20179 years ago

Similar Papers

A Supervised Approach to Extractive Summarisation of Scientific Papers

83% match1 repo2612017

Non-Parametric Memory Guidance for Multi-Document Summarization

82% match1 repo2023

Sentence Embeddings as an intermediate target in end-to-end summarisation

82% match2025

MeanSum: A Neural Model for Unsupervised Multi-document Abstractive Summarization

82% match1 repo1142018

Content Selection in Deep Learning Models of Summarization

82% match1 repo1062018

Data-driven Summarization of Scientific Articles

81% match1 repo102018

Cite this paper

@article{hasselqvist2017querybased,
  title  = {Query-Based Abstractive Summarization Using Neural Networks},
  author = {Johan Hasselqvist and Niklas Helmertz and Mikael Kågebäck},
  year   = {2017},
  eprint = {1712.06100},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1712.06100}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1712.06100.svg)](https://codeofpaper.com/paper/1712.06100)

Discussion