pith. sign in

arxiv: 2005.06377 · v3 · pith:PYHNEQPZnew · submitted 2020-05-13 · 💻 cs.CL · cs.IR· cs.LG

SueNes: A Weakly Supervised Approach to Evaluating Single-Document Summarization via Negative Sampling

classification 💻 cs.CL cs.IRcs.LG
keywords referencesummaryapproachevaluationlinguisticmetricssummariessummarization
0
0 comments X
read the original abstract

Canonical automatic summary evaluation metrics, such as ROUGE, focus on lexical similarity which cannot well capture semantics nor linguistic quality and require a reference summary which is costly to obtain. Recently, there have been a growing number of efforts to alleviate either or both of the two drawbacks. In this paper, we present a proof-of-concept study to a weakly supervised summary evaluation approach without the presence of reference summaries. Massive data in existing summarization datasets are transformed for training by pairing documents with corrupted reference summaries. In cross-domain tests, our strategy outperforms baselines with promising improvements, and show a great advantage in gauging linguistic qualities over all metrics.

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.