A New Approach to Overgenerating and Scoring Abstractive Summaries

NAACL 2021  ·  Kaiqiang Song, Bingqing Wang, Zhe Feng, Fei Liu ·

We propose a new approach to generate multiple variants of the target summary with diverse content and varying lengths, then score and select admissible ones according to users' needs. Abstractive summarizers trained on single reference summaries may struggle to produce outputs that achieve multiple desirable properties, i.e., capturing the most important information, being faithful to the original, grammatical and fluent. In this paper, we propose a two-staged strategy to generate a diverse set of candidate summaries from the source text in stage one, then score and select admissible ones in stage two. Importantly, our generator gives a precise control over the length of the summary, which is especially well-suited when space is limited. Our selectors are designed to predict the optimal summary length and put special emphasis on faithfulness to the original text. Both stages can be effectively trained, optimized and evaluated. Our experiments on benchmark summarization datasets suggest that this paradigm can achieve state-of-the-art performance.

PDF Abstract NAACL 2021 PDF NAACL 2021 Abstract


Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Benchmark
Text Summarization GigaWord Best Summary Length ROUGE-1 39.27 # 10
ROUGE-2 20.40 # 8
ROUGE-L 37.75 # 1


No methods listed for this paper. Add relevant methods here