.png){kind=icon}
返回
Semantic Drift in Multilingual Representations
.png){kind=icon}
OA
AI
DOI：10.1162/coli_a_00382.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Multilingual representations have mostly been evaluated based on their performance on specific tasks. In this article, we look beyond engineering goals and analyze the relations between languages in computational representations. We introduce a methodology for comparing languages based on their organization of semantic concepts. We propose to conduct an adapted version of representational similarity analysis of a selected set of concepts in computational multilingual representations. Using this analysis method, we can reconstruct a phylogenetic tree that closely resembles those assumed by linguistic experts. These results indicate that multilingual distributional representations that are only trained on monolingual text and bilingual dictionaries preserve relations between languages without the need for any etymological information. In addition, we propose a measure to identify semantic drift between language families. We perform experiments on word-based and sentence-based multilingual models and provide both quantitative results and qualitative examples. Analyses of semantic drift in multilingual representations can serve two purposes: They can indicate unwanted characteristics of the computational models and they provide a quantitative means to study linguistic phenomena across languages.
期刊
IF:
5.3
论文数:
837
被引数:
2.7K
机构
引用论文
Evolution of Surface Morphology With Hydrogen Dilution During Silicon Epitaxy by Mesoplasma CVD
PREAI
分享收藏Two decades of statistical language modeling: Where do we go from here?统计语言建模二十年: 我们何去何从？.png)
PROCEEDINGS OF THE IEEEOAAI
PROCEEDINGS OF THE IEEEIF25.9
OAAI分享收藏
Economic benefit evaluation method for the micro-grid renewable energy system operation微网可再生能源系统运行经济效益评价方法
PREAI
分享收藏分享收藏
查看更多内容