A Study of Methods for the Generation of Domain-Aware Word Embeddings
A Study of Methods for the Generation of Domain-Aware Word Embeddings
复制标题
DOI：
10.1145/3397271.3401287
复制
发表时间：
2020-07
期刊：
影响因子：
--
通讯作者：
Dominic Seyler;Chengxiang Zhai
中科院分区：
文献类型：
--
作者：
Dominic Seyler;Chengxiang Zhai
词嵌入是许多文本数据应用程序的重要组件。在大多数工作中，使用在一般文本语料库上训练的“开箱即用”嵌入，但当应用于特定领域的设置时，它们可能不太有效。因此，如何创建“领域感知”的词嵌入是一个有趣的开放研究问题。在本文中，我们研究了三种方法来创建领域感知的词嵌入的基础上，一般和特定领域的文本语料库，包括拼接的嵌入向量，加权融合的文本数据，对齐的嵌入向量的插值。尽管所研究的策略是为特定领域的任务量身定制的，但它们足够普遍，可以应用于任何领域，而不是特定于单个任务。实验结果表明，三种方法都能很好地工作，但插值方法的效果始终最好。
Word embeddings are essential components for many text data applications. In most work, "out-of-the-box" embeddings trained on general text corpora are used, but they can be less effective when applied to domain-specific settings. Thus, how to create "domain-aware" word embeddings is an interesting open research question. In this paper, we study three methods for creating domain-aware word embeddings based on both general and domain-specific text corpora, including concatenation of embedding vectors, weighted fusion of text data, and interpolation of aligned embedding vectors. Even though the investigated strategies are tailored for domain-specific tasks, they are general enough to be applied to any domain and are not specific to a single task. Experimental results show that all three methods can work well, however, the interpolation method consistently works best.