.png){kind=icon}
返回
Language Embeddings Sometimes Contain Typological Generalizations
.png){kind=icon}
OA
AI
DOI：10.1162/coli_a_00491.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
To what extent can neural network models learn generalizations about language structure, and how do we find out what they have learned? We explore these questions by training neural models for a range of natural language processing tasks on a massively multilingual dataset of Bible translations in 1,295 languages. The learned language representations are then compared to existing typological databases as well as to a novel set of quantitative syntactic and morphological features obtained through annotation projection. We conclude that some generalizations are surprisingly close to traditional features from linguistic typology, but that most of our models, as well as those of previous work, do not appear to have made linguistically meaningful generalizations. Careful attention to details in the evaluation turns out to be essential to avoid false positives. Furthermore, to encourage continued work in this field, we release several resources covering most or all of the languages in our data: (1) multiple sets of language representations, (2) multilingual word embeddings, (3) projected and predicted syntactic and morphological features, (4) software to provide linguistically sound evaluations of language representations.
期刊
IF:
5.3
论文数:
837
被引数:
2.7K
机构
引用论文
Testing the conceptual and operational underpinnings of field herbivory assays: Does variation in predictability of resources, assay design, and deployment method affect outcomes?测试实地食草性测定的概念和操作基础：资源可预测性的变化、测定设计和部署方法是否影响结果？
OAAI
OAAI分享收藏Evolved structure of language shows lineage-specific trends in word-order universals.png)
NATURE
NATUREIF48.5
PREAI
分享收藏In vitro propagation of Leucocroton havanensis Borhidi (Euphorbiaceae): A rare serpentine-endemic species of CubaIn vitro繁殖Leucocroton havanensis Borhidi（大戟科）：古巴一种罕见的蛇纹石土著种
PREAI
分享收藏
查看更多内容