arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1601.03764cs.CLcs.LGstat.ML
收藏

词义的线性代数结构及其在一词多义中的应用

Linear Algebraic Structure of Word Senses, with Applications to Polysemy

Princeton University(普林斯顿大学)

Sanjeev Arora, Yuanzhi Li, Yingyu Liang, Tengyu Ma, Andrej Risteski

摘要:

词嵌入在自然语言处理和信息检索中是普遍存在的,但当词是多义词时,它们表示什么还不清楚。在这里,它表明,多个词的意义驻留在线性叠加内的词嵌入和简单的稀疏编码可以恢复向量,近似捕获的意义。我们的方法的成功,适用于几种嵌入方法,在数学上解释使用随机游走的话语模型的变体(Arora等人,2016年)。我们的技术的一个新颖的方面是,每个提取的词义都伴随着大约2000个“话语原子”,给出了一个简洁的描述,其他词共同出现的词义。话语原子可以是独立的兴趣,并使该方法潜在地更有用。实证检验是用来验证和支持的理论。

英文摘要:

Word embeddings are ubiquitous in NLP and information retrieval, but it is unclear what they represent when the word is polysemous. Here it is shown that multiple word senses reside in linear superposition within the word embedding and simple sparse coding can recover vectors that approximately capture the senses. The success of our approach, which applies to several embedding methods, is mathematically explained using a variant of the random walk on discourses model (Arora et al., 2016). A novel aspect of our technique is that each extracted word sense is accompanied by one of about 2000 "discourse atoms" that gives a succinct description of which other words co-occur with that word sense. Discourse atoms can be of independent interest, and make the method potentially more useful. Empirical tests are used to verify and support the theory.

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。

↑