pith. sign in

arxiv: 1704.04530 · v2 · pith:4H2X2UEGnew · submitted 2017-04-14 · 💻 cs.CL

Neural Extractive Summarization with Side Information

classification 💻 cs.CL
keywords informationsidesummarizationextractivedocumentsingle-documentarticlesattention
0
0 comments X
read the original abstract

Most extractive summarization methods focus on the main body of the document from which sentences need to be extracted. However, the gist of the document may lie in side information, such as the title and image captions which are often available for newswire articles. We propose to explore side information in the context of single-document extractive summarization. We develop a framework for single-document summarization composed of a hierarchical document encoder and an attention-based extractor with attention over side information. We evaluate our model on a large scale news dataset. We show that extractive summarization with side information consistently outperforms its counterpart that does not use any side information, in terms of both informativeness and fluency.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. What is this Article about? Extreme Summarization with Topic-aware Convolutional Neural Networks

    cs.CL 2019-07 unverdicted novelty 8.0

    Introduces extreme summarization as a one-sentence abstractive task, a new BBC dataset, and a topic-conditioned CNN model that outperforms extractive and abstractive baselines on automatic and human evaluations.

  2. Ranking sentences from product description & bullets for better search

    cs.IR 2019-07 unverdicted novelty 4.0

    Two RL-based extractive summarization models rank sentences from product fields by leveraging titles and click-through logs to improve search relevance.