强化学习取代监督学习：基于深度强化学习的查询聚焦摘要
Reinforcement Replaces Supervision: Query focused Summarization using Deep Reinforcement Learning
AI总结：
本文提出用深度强化学习替代监督学习解决查询聚焦摘要，通过策略梯度网络结合ROUGE、BLEU及基于聚类假设的语义相似度奖励，在ELI5上ROUGE-L提升10点，并贡献了新的测试数据集。
摘要：
查询聚焦摘要（QfS）涉及根据查询从文档中生成摘要的系统。受以下见解的启发：强化学习（RL）为自然语言生成提供了对监督学习（SL）的泛化，并因此在经验上比SL表现更好，我们采用基于RL的方法来完成这一QfS任务。此外，我们还解决了在Transformer中使用教师强制（Teacher Forcing）与采用RL之间的冲突。我们开发了多个策略梯度网络，并在各种奖励信号上进行训练：ROUGE、BLEU和语义相似度，这使得在基准数据集（ELI5）上的ROUGE-L指标比当前最先进方法提高了10个点。我们还展示了我们的方法在另一个基准数据集（DebatePedia）上的零样本设置下的性能——我们的方法取得了与专门在DebatePedia上训练的基线相当的结果。为了辅助RL训练，我们提出了一种更好的语义相似度奖励，该奖励通过使用聚类假设（Cluster Hypothesis）开发的新型段落嵌入方案实现。最后，我们贡献了一个黄金标准测试数据集，以进一步推动QfS和长形式问答（LfQA）的研究。
英文摘要：
Query-focused Summarization (QfS) deals with systems that generate summaries from document(s) based on a query. Motivated by the insight that Reinforcement Learning (RL) provides a generalization to Supervised Learning (SL) for Natural Language Generation, and thereby performs better (empirically) than SL, we use an RL-based approach for this task of QfS. Additionally, we also resolve the conflict of employing RL in Transformers with Teacher Forcing. We develop multiple Policy Gradient networks, trained on various reward signals: ROUGE, BLEU, and Semantic Similarity, which lead to a 10-point improvement over the State-of-the-Art approach on the ROUGE-L metric for a benchmark dataset (ELI5). We also show performance of our approach in zero-shot setting for another benchmark dataset (DebatePedia) -- our approach leads to results comparable to baselines, which were specifically trained on DebatePedia. To aid the RL training, we propose a better semantic similarity reward, enabled by a novel Passage Embedding scheme developed using Cluster Hypothesis. Lastly, we contribute a gold-standard test dataset to further research in QfS and Long-form Question Answering (LfQA).
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
