arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2106.00352cs.CLcs.AI
收藏

复制和扩展“因为它们的树库泄漏”:图同构、协变量和解析器性能

Replicating and Extending "Because Their Treebanks Leak": Graph Isomorphism, Covariants, and Parser Performance

Universidade da Coruña(拉科鲁尼亚大学);CITIC(信息与通信技术研究中心);University of Copenhagen(哥本哈根大学)

Mark Anderson, Anders Søgaard, Carlos Gómez Rodríguez

摘要:

Søgaard(2020)获得的结果表明,在测试数据中出现的树与训练集中的树同构的比例说明了解析器性能的非平凡变化。与NLP中的其他统计分析类似,结果基于评估线性回归。然而,这项研究存在方法问题,而且使用的样本量很小,导致结果不可靠。我们提出了一个复制的研究中,我们也斌的句子长度,发现只有一小部分的句子不同的性能与图同构。此外,当控制协变时,在解析器性能和图同构之间观察到的相关性消失了。然而,在一个受控实验中,协变量保持固定,我们确实观察到了很强的相关性。我们认为,从这样的统计分析中得出的结论需要加以调整,而对照实验可以通过更容易地剔除因素来补充它们。

英文摘要:

Søgaard (2020) obtained results suggesting the fraction of trees occurring in the test data isomorphic to trees in the training set accounts for a non-trivial variation in parser performance. Similar to other statistical analyses in NLP, the results were based on evaluating linear regressions. However, the study had methodological issues and was undertaken using a small sample size leading to unreliable results. We present a replication study in which we also bin sentences by length and find that only a small subset of sentences vary in performance with respect to graph isomorphism. Further, the correlation observed between parser performance and graph isomorphism in the wild disappears when controlling for covariants. However, in a controlled experiment, where covariants are kept fixed, we do observe a strong correlation. We suggest that conclusions drawn from statistical analyses like this need to be tempered and that controlled experiments can complement them by more readily teasing factors apart.

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。

↑