Answers Unite! Unsupervised Metrics for Reinforced Summarization Models

Abstract : Abstractive summarization approaches based on Reinforcement Learning (RL) have recently been proposed to overcome classical likelihood maximization. RL enables to consider complex, possibly non differentiable, metrics that globally assess the quality and relevance of the generated outputs. ROUGE, the most used summarization metric, is known to suffer from bias towards lexical similarity as well as from sub-optimal accounting for fluency and readability of the generated abstracts. We thus explore and propose alternative evaluation measures: the reported human-evaluation analysis shows that the proposed metrics, based on Question Answering, favorably compare to ROUGE – with the additional property of not requiring reference summaries. Training a RL-based model on these metrics leads to improvements (both in terms of human or automated metrics) over current approaches that use ROUGE as reward.
Complete list of metadatas

https://hal.sorbonne-universite.fr/hal-02350999
Contributor : Benjamin Piwowarski <>
Submitted on : Wednesday, November 6, 2019 - 11:22:06 AM
Last modification on : Wednesday, November 13, 2019 - 10:16:55 AM

Links full text

Identifiers

Citation

Thomas Scialom, Sylvain Lamprier, Benjamin Piwowarski, Jacopo Staiano. Answers Unite! Unsupervised Metrics for Reinforced Summarization Models. 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), Nov 2019, Hong Kong, China. pp.3237-3247, ⟨10.18653/v1/D19-1320⟩. ⟨hal-02350999⟩

Share

Metrics

Record views

19