Work

Bottom-Up Abstractive Summarization

Year: 2018

Type: conference-paper

Abstract: Neural network-based methods for abstractive summarization produce outputs that are more fluent than other techniques, but which can be poor at content selection.This work proposes a simple technique for addressing this issue: use a data-efficient content selector to overdetermine phrases in a source document that should be part of the summary.We use this selector as a bottom-up attention step to constrain the model to likely phrases.We show that this approach improves the ability to compress text, while still generating fluent summaries.This two-step process is both simpler and higher performing than other end-to-end content selection models, leading to significant improvements on ROUGE for both the CNN-DM and NYT corpus.Furthermore, the content selector can be trained with as little as 1,000 sentences, making it easy to transfer a trained summarizer to a new domain.

Source: Conference on Empirical Methods in Natural Language Processing (EMNLP)

DOI: 10.18653/v1/d18-1443

Authors: Sebastian Gehrmann, Yuntian Deng, Alexander Rush

Institution: Harvard University

Language: English

Topic: Topic Modeling

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funders: National Institutes of Health, Samsung

Award: SCH: INT: Collaborative Research Intelligent Information Sharing: Advancing Teamwork in Complex Care