当前位置: X-MOL 学术arXiv.cs.CL › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Paraphrases do not explain word analogies
arXiv - CS - Computation and Language Pub Date : 2021-02-23 , DOI: arxiv-2102.11749
Louis Fournier, Ewan Dunbar

Many types of distributional word embeddings (weakly) encode linguistic regularities as directions (the difference between "jump" and "jumped" will be in a similar direction to that of "walk" and "walked," and so on). Several attempts have been made to explain this fact. We respond to Allen and Hospedales' recent (ICML, 2019) theoretical explanation, which claims that word2vec and GloVe will encode linguistic regularities whenever a specific relation of paraphrase holds between the four words involved in the regularity. We demonstrate that the explanation does not go through: the paraphrase relations needed under this explanation do not hold empirically.

中文翻译:

释义不能解释单词的类比

许多类型的分布词嵌入(弱地)将语言规律性编码为方向(“跳跃”和“跳跃”之间的差异与“行走”和“行走”的方向相似,依此类推)。已经进行了几次尝试来解释这个事实。我们回应了Allen和Hospedales的最新理论解释(ICML,2019),该理论认为word2vec和GloVe将在规则性涉及的四个单词之间保持特定的释义关系时对语言规则性进行编码。我们证明该解释没有通过:在该解释下所需的释义关系在经验上不成立。
更新日期:2021-02-24
down
wechat
bug