文本颜色对词嵌入的影响
Effect of Text Color on Word Embeddings
摘要：
在自然场景和文档中，我们可以找到文本与其颜色之间的相关性。例如，“热”这个词通常用红色印刷，而“冷”通常用蓝色印刷。这种相关性可以被认为是表示单词之间语义差异的特征。基于这一观察，我们提出了将文本颜色用于词嵌入的想法。虽然纯文本的词嵌入（例如word2vec）非常成功，但它们通常表示反义词相似，因为它们通常在句子中可以互换。在本文中，我们尝试了两个任务，以验证文本颜色在理解单词的含义，特别是在识别同义词和反义词的有用性。首先，我们量化了书籍封面图像中单词的颜色分布，并分析了颜色与单词含义之间的相关性。其次，我们尝试以词的颜色分布作为约束来重新训练词嵌入。通过观察重新训练前后同义词和反义词的词嵌入的变化，我们的目标是了解在加入文本颜色信息时，哪些词的词嵌入会产生积极或消极的影响。
英文摘要：
In natural scenes and documents, we can find the correlation between a text and its color. For instance, the word, "hot", is often printed in red, while "cold" is often in blue. This correlation can be thought of as a feature that represents the semantic difference between the words. Based on this observation, we propose the idea of using text color for word embeddings. While text-only word embeddings (e.g. word2vec) have been extremely successful, they often represent antonyms as similar since they are often interchangeable in sentences. In this paper, we try two tasks to verify the usefulness of text color in understanding the meanings of words, especially in identifying synonyms and antonyms. First, we quantify the color distribution of words from the book cover images and analyze the correlation between the color and meaning of the word. Second, we try to retrain word embeddings with the color distribution of words as a constraint. By observing the changes in the word embeddings of synonyms and antonyms before and after re-training, we aim to understand the kind of words that have positive or negative effects in their word embeddings when incorporating text color information.
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。
