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 2310.15905cs.CLcs.AIcs.LG
收藏

探针是你所需的一切吗?指示任务作为探针嵌入空间的替代方案

Is Probing All You Need? Indicator Tasks as an Alternative to Probing Embedding Spaces

Bar-Ilan University(巴伊兰大学)

Tal Levy, Omer Goldman, Reut Tsarfaty

AI总结:

本文提出“指示任务”作为探针的替代方案,用于查询嵌入空间属性,避免分类器训练导致的纠缠,并通过性别去偏和形态信息擦除案例证明其能更准确反映信息捕获与移除情况。

摘要:

识别和控制词向量表示中编码的不同类型语言信息的能力具有许多应用场景,特别是对于可解释性和偏差消除。这通常通过一组简单的分类任务(称为探针)来评估嵌入空间中编码的信息。然而,可训练分类器的引入导致探针结果与分类器本质之间产生纠缠。因此,当代关于探针的研究包含了不涉及训练辅助模型的任务。在本研究中,我们引入了“指示任务”这一术语,用于指代那些不可训练的任务,它们被用来查询嵌入空间中是否存在某些特定属性。我们指出,这类任务可能指向与探针相反的方向,而这种矛盾使得判断嵌入空间中是否存在某属性变得复杂。我们通过两个测试案例验证了我们的主张:一个涉及性别去偏,另一个涉及从嵌入空间中擦除形态信息。我们表明,与探针相比,应用合适的指示任务能够更准确地反映所捕获和移除的信息。因此我们得出结论,在从嵌入表示中提取信息时,应该实施并考虑指示任务。

英文摘要:

The ability to identify and control different kinds of linguistic information encoded in vector representations of words has many use cases, especially for explainability and bias removal. This is usually done via a set of simple classification tasks, termed probes, to evaluate the information encoded in the embedding space. However, the involvement of a trainable classifier leads to entanglement between the probe's results and the classifier's nature. As a result, contemporary works on probing include tasks that do not involve training of auxiliary models. In this work we introduce the term indicator tasks for non-trainable tasks which are used to query embedding spaces for the existence of certain properties, and claim that this kind of tasks may point to a direction opposite to probes, and that this contradiction complicates the decision on whether a property exists in an embedding space. We demonstrate our claims with two test cases, one dealing with gender debiasing and another with the erasure of morphological information from embedding spaces. We show that the application of a suitable indicator provides a more accurate picture of the information captured and removed compared to probes. We thus conclude that indicator tasks should be implemented and taken into consideration when eliciting information from embedded representations.

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。

↑