OBJECTIVE FUNCTION LEARNING TO MATCH HUMAN JUDGEMENTS FOR OPTIMIZATION-BASED SUMMARIZATION
2018Β
Supervised summarization systems usually rely on supervision at the sentence or n-gram level provided by automatic metrics like ROUGE, which act as noisy proxies for human judgments. In this work, we learn a summary-level scoring function π including human judgments as supervision and automatically generated data as regularization. We extract summaries with a genetic algorithm using π as a fitness function. We observe strong and promising performances across datasets in both automatic and manual evaluation.
Keywords:
- Correction
- Source
- Cite
- Save
- Machine Reading By IdeaReader
25
References
19
Citations
NaN
KQI