arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2407.12342cs.CL
收藏

基于弱监督特征选择的词嵌入降维

Word Embedding Dimension Reduction via Weakly-Supervised Feature Selection

University of Southern California(南加州大学)

Jintang Xue, Yun-Cheng Wang, Chengwei Wei, C. -C. Jay Kuo

AI总结:

针对词嵌入随词汇量增长维度升高、模型规模大且资源消耗高的问题,提出弱监督特征选择方法WordFS,在多任务上以更低计算成本实现优于现有降维方法的性能,并开源代码。

摘要:

作为自然语言处理中的一项基础任务,词嵌入将每个单词转换为向量空间中的一种表示。词嵌入面临的一个挑战是,随着词汇量增长,向量空间的维度会增加,这可能导致模型规模极为庞大。存储和处理词向量需要大量资源,对于移动边缘设备应用而言尤其如此。本文对词嵌入降维展开研究。为平衡计算成本与性能,我们提出了一种高效且有效的弱监督特征选择方法,名为WordFS。该方法有两种变体,各自采用新颖的特征选择准则。在多种任务(例如单词与句子相似度、二分类与多分类任务)上开展的实验表明,所提出的WordFS模型以更低的计算成本优于其他降维方法。我们已随论文发布代码以供复现研究结果。

英文摘要:

As a fundamental task in natural language processing, word embedding converts each word into a representation in a vector space. A challenge with word embedding is that as the vocabulary grows, the vector space's dimension increases, which can lead to a vast model size. Storing and processing word vectors are resource-demanding, especially for mobile edge-devices applications. This paper explores word embedding dimension reduction. To balance computational costs and performance, we propose an efficient and effective weakly-supervised feature selection method named WordFS. It has two variants, each utilizing novel criteria for feature selection. Experiments on various tasks (e.g., word and sentence similarity and binary and multi-class classification) indicate that the proposed WordFS model outperforms other dimension reduction methods at lower computational costs. We have released the code for reproducibility along with the paper.

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。

↑