arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1802.06196cs.CL
收藏

分布式叙词表的网络嵌入能否与词向量相结合更好地表示?

Can Network Embedding of Distributional Thesaurus be Combined with Word Vectors for Better Representation?

IIT Kharagpur, India(印度理工学院卡格拉普尔分校(IIT Kharagpur))

Abhik Jana, Pawan Goyal

摘要:

近年来,从文本中学习的单词的分布式表示已被证明在各种自然语言处理任务中是成功的。虽然一些方法将单词表示为使用预测模型(Word2vec)或基于密集计数的模型(GloVe)从文本计算的向量,但其他方法试图在分布式词库网络结构中表示这些,其中单词的邻域是具有足够上下文重叠的单词集合。受最近网络嵌入技术(DeepWalk、LINE、node2vec等)研究激增的推动,我们把一个分布式词库网络转换成密集的词向量,并研究分布式词库嵌入在提高整体词表示方面的有用性。这是我们第一次尝试将分布式词库嵌入所获得的单词表示与最先进的单词表示相结合,有助于在针对单词相似性和相关性,同义词检测,类比检测等NLP任务进行评估时显着提高性能。此外,我们表明,即使不使用任何手工制作的词汇资源,我们可以拿出表示具有可比的性能在单词相似性和相关性的任务相比,表示的词汇资源已被使用。

英文摘要:

Distributed representations of words learned from text have proved to be successful in various natural language processing tasks in recent times. While some methods represent words as vectors computed from text using predictive model (Word2vec) or dense count based model (GloVe), others attempt to represent these in a distributional thesaurus network structure where the neighborhood of a word is a set of words having adequate context overlap. Being motivated by recent surge of research in network embedding techniques (DeepWalk, LINE, node2vec etc.), we turn a distributional thesaurus network into dense word vectors and investigate the usefulness of distributional thesaurus embedding in improving overall word representation. This is the first attempt where we show that combining the proposed word representation obtained by distributional thesaurus embedding with the state-of-the-art word representations helps in improving the performance by a significant margin when evaluated against NLP tasks like word similarity and relatedness, synonym detection, analogy detection. Additionally, we show that even without using any handcrafted lexical resources we can come up with representations having comparable performance in the word similarity and relatedness tasks compared to the representations where a lexical resource has been used.

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。

↑