Does Typological Blinding Impede Cross-Lingual Sharing?
Does Typological Blinding Impede Cross-Lingual Sharing?
复制标题
类型致盲是否会阻碍跨语言共享？
DOI：
--
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
Isabelle Augenstein
中科院分区：
文献类型：
--
作者：
Johannes Bjerva;Isabelle Augenstein
弥合高资源语言和低资源语言之间的性能差距一直是以前许多工作的重点。来自世界语言结构地图集（WALS）等数据库的类型学特征是这方面的主要候选者，因为即使对于资源非常低的语言也存在这样的数据。然而，以前的工作只发现使用类型学信息的小好处。我们的假设是，在跨语言环境中训练的模型将从输入数据中获取类型学线索，从而掩盖了显式使用这些特征的实用性。我们验证了这一假设，盲模型的类型信息，并调查如何跨语言共享和性能的影响。我们的模型是基于一个跨语言的架构，其中管理语言之间的共享的潜在权重是在训练过程中学习。我们表明，（i）防止这种模式利用类型严重降低性能，而控制实验重申，（ii）鼓励共享根据类型多少提高性能。
Bridging the performance gap between high- and low-resource languages has been the focus of much previous work. Typological features from databases such as the World Atlas of Language Structures (WALS) are a prime candidate for this, as such data exists even for very low-resource languages. However, previous work has only found minor benefits from using typological information. Our hypothesis is that a model trained in a cross-lingual setting will pick up on typological cues from the input data, thus overshadowing the utility of explicitly using such features. We verify this hypothesis by blinding a model to typological information, and investigate how cross-lingual sharing and performance is impacted. Our model is based on a cross-lingual architecture in which the latent weights governing the sharing between languages is learnt during training. We show that (i) preventing this model from exploiting typology severely reduces performance, while a control experiment reaffirms that (ii) encouraging sharing according to typology somewhat improves performance.
DOI：
10.18653/v1/2021.starsem-1.22
发表时间：
2020-08
期刊：
--
影响因子：
--
作者：
Wei Zhao;Steffen Eger;Johannes Bjerva;Isabelle Augenstein
通讯作者：
Wei Zhao;Steffen Eger;Johannes Bjerva;Isabelle Augenstein
影响因子：
4.3
作者：
Augenstein, Isabelle;Derczynski, Leon;Bontcheva, Kalina
通讯作者：
Bontcheva, Kalina