arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2202.00486cs.CLcs.AIcs.IRcs.LGstat.ML
收藏

对词和关系表征的理论理解

Towards a Theoretical Understanding of Word and Relation Representation

University of Edinburgh(爱丁堡大学)

Carl Allen

摘要:

通过向量或嵌入表示单词,可以实现计算推理,并且是自动化自然语言任务的基础。例如,如果相似词的词嵌入包含相似值,则可以容易地评估词相似性,而从它们的拼写来判断通常是不可能的(例如cat /feline),并且预先确定和存储所有词之间的相似性是极其耗时、记忆密集和主观的。我们专注于从文本语料库和知识图谱中学习的词嵌入。几种众所周知的算法通过学习预测出现在每个单词周围的那些单词来在无监督的基础上从文本中学习词嵌入,例如word 2 vec和GloVe。已知这种词嵌入的参数反映词共现统计,但它们如何捕获语义含义一直不清楚。知识图谱表示模型学习实体(单词、人、地点等)的表示。以及它们之间的关系,通常通过训练模型以监督的方式预测已知事实。尽管事实上预测准确性稳步提高,但人们对实现这一点的潜在结构知之甚少。对潜在语义结构如何在词嵌入和知识图谱表示的几何结构中编码的有限理解使得改善其性能、可靠性或可解释性的原则性手段不清楚。为了解决这个问题:1.我们从理论上证明了经验观察,即通过诸如word 2 vec和GloVe的算法学习的词嵌入之间的特定几何关系对应于词之间的语义关系;以及2.我们将语义和几何之间的这种对应关系扩展到知识图谱的实体和关系,提供了与词嵌入相关联的知识图谱表示的潜在结构的模型。

英文摘要:

Representing words by vectors, or embeddings, enables computational reasoning and is foundational to automating natural language tasks. For example, if word embeddings of similar words contain similar values, word similarity can be readily assessed, whereas judging that from their spelling is often impossible (e.g. cat /feline) and to predetermine and store similarities between all words is prohibitively time-consuming, memory intensive and subjective. We focus on word embeddings learned from text corpora and knowledge graphs. Several well-known algorithms learn word embeddings from text on an unsupervised basis by learning to predict those words that occur around each word, e.g. word2vec and GloVe. Parameters of such word embeddings are known to reflect word co-occurrence statistics, but how they capture semantic meaning has been unclear. Knowledge graph representation models learn representations both of entities (words, people, places, etc.) and relations between them, typically by training a model to predict known facts in a supervised manner. Despite steady improvements in fact prediction accuracy, little is understood of the latent structure that enables this. The limited understanding of how latent semantic structure is encoded in the geometry of word embeddings and knowledge graph representations makes a principled means of improving their performance, reliability or interpretability unclear. To address this: 1. we theoretically justify the empirical observation that particular geometric relationships between word embeddings learned by algorithms such as word2vec and GloVe correspond to semantic relations between words; and 2. we extend this correspondence between semantics and geometry to the entities and relations of knowledge graphs, providing a model for the latent structure of knowledge graph representation linked to that of word embeddings.

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。

↑