arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.07560cs.CL
收藏

对句子简化中自动求值的再思考

Rethinking Automatic Evaluation in Sentence Simplification

Sorbonne Université(索邦大学);CNRS(法国国家科学研究中心);LIP6(巴黎第六大学计算机科学实验室);reciTAL;Facebook AI Research(Facebook人工智能研究院);Inria(法国国家信息与自动化研究所)

Thomas Scialom, Louis Martin, Jacopo Staiano, Éric Villemonte de la Clergerie, Benoît Sagot

摘要:

自动评测是自然语言生成领域的一个研究热点。在句子简化的上下文中,这尤其具有挑战性:这项任务本质上要求用具有相同含义的简单单词替换复杂单词。这限制了BLEU等基于n-gram的度量的有效性。与NLG的最新进展齐头并进,新的指标已经被提出,例如用于机器翻译的BERTScore。总之,QuestEval度量建议通过提问来自动比较两个文本。在本文中,我们首先提出了一个简单的修改QuestEval允许它处理句子简化。然后,我们广泛评估的相关性w.r.t.人类判断的几个指标,包括最近的BERTScore和QuestEval,并显示后者获得最先进的相关性,优于标准指标,如BLEU和SARI。更重要的是,我们还表明,很大一部分的相关性实际上是虚假的所有指标。为了进一步研究这种现象,我们发布了一个新的评估简化语料库,这次不是由系统生成,而是由人类编写。这使我们能够去除虚假的相关性,并得出与原始相关性非常不同的结论,从而更好地理解这些指标。特别是,我们对大多数传统指标的相关性非常低表示担忧。我们的研究结果表明,意义保存的唯一显着措施是我们的适应QuestEval。

英文摘要:

Automatic evaluation remains an open research question in Natural Language Generation. In the context of Sentence Simplification, this is particularly challenging: the task requires by nature to replace complex words with simpler ones that shares the same meaning. This limits the effectiveness of n-gram based metrics like BLEU. Going hand in hand with the recent advances in NLG, new metrics have been proposed, such as BERTScore for Machine Translation. In summarization, the QuestEval metric proposes to automatically compare two texts by questioning them. In this paper, we first propose a simple modification of QuestEval allowing it to tackle Sentence Simplification. We then extensively evaluate the correlations w.r.t. human judgement for several metrics including the recent BERTScore and QuestEval, and show that the latter obtain state-of-the-art correlations, outperforming standard metrics like BLEU and SARI. More importantly, we also show that a large part of the correlations are actually spurious for all the metrics. To investigate this phenomenon further, we release a new corpus of evaluated simplifications, this time not generated by systems but instead, written by humans. This allows us to remove the spurious correlations and draw very different conclusions from the original ones, resulting in a better understanding of these metrics. In particular, we raise concerns about very low correlations for most of traditional metrics. Our results show that the only significant measure of the Meaning Preservation is our adaptation of QuestEval.

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。

↑