The seminar run from 11am to 12pm. Please register online
Date: 9th September 2019
Thomas Scialom, AI Research Scientist & Partner at reciTAL, Paris, France
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 suboptimal 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 compares to ROUGE – with the additional property of not requiring reference summaries. Training an RL based model on these metrics leads to improvements (both in terms of human or automated metrics) over current approaches that use ROUGE as a reward.