学习预测常识生成的概念顺序
Learning to Predict Concept Ordering for Common Sense Generation
AI总结：
本研究系统探讨了输入概念顺序对常识生成质量的影响，发现BART-large模型表现最佳，而人类重排的概念顺序能实现最优生成。
摘要：
先前的研究表明，向常识生成器展示概念的顺序起着重要作用，会影响生成句子的质量。然而，确定给定概念集合的最佳顺序，使得预训练生成器能够生成涵盖所有概念的自然句子，仍然是一个挑战。为了理解输入概念顺序与生成句子质量之间的关系，我们进行了一项系统研究，考虑了多种语言模型和概念排序策略。我们发现，使用概念在CommonGen训练数据中出现的顺序进行微调时，根据多种评估指标衡量，BART-large模型始终优于本研究中考虑的所有其他LM。此外，基于GPT3的大型语言模型变体在此任务上不一定优于小得多的LM，即使在任务特定训练数据上进行微调也是如此。有趣的是，人类标注者在手动编写涵盖这些概念的句子时，会显著重排输入概念集合，并且这种排序无论使用哪种LM进行生成，都能提供最佳的句子生成，优于概率概念排序基线。
英文摘要：
Prior work has shown that the ordering in which concepts are shown to a commonsense generator plays an important role, affecting the quality of the generated sentence. However, it remains a challenge to determine the optimal ordering of a given set of concepts such that a natural sentence covering all the concepts could be generated from a pretrained generator. To understand the relationship between the ordering of the input concepts and the quality of the generated sentences, we conduct a systematic study considering multiple language models (LMs) and concept ordering strategies. We find that BART-large model consistently outperforms all other LMs considered in this study when fine-tuned using the ordering of concepts as they appear in CommonGen training data as measured using multiple evaluation metrics. Moreover, the larger GPT3-based large language models (LLMs) variants do not necessarily outperform much smaller LMs on this task, even when fine-tuned on task-specific training data. Interestingly, human annotators significantly reorder input concept sets when manually writing sentences covering those concepts, and this ordering provides the best sentence generations independently of the LM used for the generation, outperforming a probabilistic concept ordering baseline
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。
