arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2010.02650cs.CL
收藏

如果束搜索是答案,那问题是什么?

If beam search is the answer, what was the question?

ETH Zürich(苏黎世联邦理工学院);Johns Hopkins University(约翰斯·霍普金斯大学);University of Cambridge(剑桥大学)

Clara Meister, Tim Vieira, Ryan Cotterell

摘要:

令人惊讶的是,神经语言生成器的精确最大后验(MAP)解码经常导致低质量的结果。相反,大多数关于语言生成任务的最先进的结果是使用束搜索获得的,尽管其搜索出错率非常高。这意味着MAP目标本身并不能表达我们在文本中所期望的属性,这就值得提出一个问题:如果束搜索是答案,那么问题是什么?我们将束搜索框定为不同解码目标的精确解,以便深入了解为什么仅在模型下的高概率可能不指示充分性。我们发现,束搜索强制均匀的信息密度在文本中,认知科学的动机属性。我们提出了一组解码目标,明确执行此属性,并发现这些目标的精确解码时遇到的问题,解码校准不良的语言生成模型。此外,我们分析了使用各种解码策略产生的文本,并看到,在我们的神经机器翻译实验中,该属性的遵守程度与BLEU密切相关。

英文摘要:

Quite surprisingly, exact maximum a posteriori (MAP) decoding of neural language generators frequently leads to low-quality results. Rather, most state-of-the-art results on language generation tasks are attained using beam search despite its overwhelmingly high search error rate. This implies that the MAP objective alone does not express the properties we desire in text, which merits the question: if beam search is the answer, what was the question? We frame beam search as the exact solution to a different decoding objective in order to gain insights into why high probability under a model alone may not indicate adequacy. We find that beam search enforces uniform information density in text, a property motivated by cognitive science. We suggest a set of decoding objectives that explicitly enforce this property and find that exact decoding with these objectives alleviates the problems encountered when decoding poorly calibrated language generation models. Additionally, we analyze the text produced using various decoding strategies and see that, in our neural machine translation experiments, the extent to which this property is adhered to strongly correlates with BLEU.

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。

↑