Fast k-best Sentence Compression
Katja Filippova, Enrique Alfonseca

TL;DR
This paper introduces a fast, local-deletion based algorithm for k-best sentence compression that outperforms ILP-based methods in speed and quality, maintaining high compression quality across multiple top results.
Contribution
The paper presents a novel, efficient algorithm for generating k-best sentence compressions using local deletion decisions, significantly improving speed over ILP-based approaches.
Findings
Algorithm is two orders of magnitude faster than ILP methods.
Compression quality remains high from top-1 to top-5 results.
Produces better compressions than recent ILP-based methods.
Abstract
A popular approach to sentence compression is to formulate the task as a constrained optimization problem and solve it with integer linear programming (ILP) tools. Unfortunately, dependence on ILP may make the compressor prohibitively slow, and thus approximation techniques have been proposed which are often complex and offer a moderate gain in speed. As an alternative solution, we introduce a novel compression algorithm which generates k-best compressions relying on local deletion decisions. Our algorithm is two orders of magnitude faster than a recent ILP-based method while producing better compressions. Moreover, an extensive evaluation demonstrates that the quality of compressions does not degrade much as we move from single best to top-five results.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsNatural Language Processing Techniques · Topic Modeling · Semantic Web and Ontologies
