SUPERT: Towards New Frontiers in Unsupervised Evaluation Metrics for Multi-Document Summarization

Yang Gao, Wei Zhao, Steffen Eger

Abstract Paper Share

Summarization Short Paper

Session 2A: Jul 6 (08:00-09:00 GMT)
Session 3B: Jul 6 (13:00-14:00 GMT)
Abstract: We study unsupervised multi-document summarization evaluation metrics, which require neither human-written reference summaries nor human annotations (e.g. preferences, ratings, etc.). We propose SUPERT, which rates the quality of a summary by measuring its semantic similarity with a pseudo reference summary, i.e. selected salient sentences from the source documents, using contextualized embeddings and soft token alignment techniques. Compared to the state-of-the-art unsupervised evaluation metrics, SUPERT correlates better with human ratings by 18- 39%. Furthermore, we use SUPERT as rewards to guide a neural-based reinforcement learning summarizer, yielding favorable performance compared to the state-of-the-art unsupervised summarizers. All source code is available at https://github.com/yg211/acl20-ref-free-eval.
You can open the pre-recorded video in a separate window.
NOTE: The SlidesLive video may display a random order of the authors. The correct author list is shown at the top of this webpage.

Similar Papers

Facet-Aware Evaluation for Extractive Summarization
Yuning Mao, Liyuan Liu, Qi Zhu, Xiang Ren, Jiawei Han,
A representative figure from paper main.445
Designing Precise and Robust Dialogue Response Evaluators
Tianyu Zhao, Divesh Lala, Tatsuya Kawahara,
A representative figure from paper main.4
On Faithfulness and Factuality in Abstractive Summarization
Joshua Maynez, Shashi Narayan, Bernd Bohnet, Ryan McDonald,
A representative figure from paper main.173
Personalized PageRank with Syntagmatic Information for Multilingual Word Sense Disambiguation
Federico Scozzafava, Marco Maru, Fabrizio Brignone, Giovanni Torrisi, Roberto Navigli,
A representative figure from paper demo.69