词语切分对上下文词表示语义内容的影响
The Impact of Word Splitting on the Semantic Content of Contextualized Word Representations
AI总结：
本文研究语言模型中未登录词被切分为子词后如何获得单向量表示，并通过语义相似性任务评估不同模型嵌入质量，发现被切分词的表示通常但并非总是更差，且其相似度值需谨慎解读。
摘要：
从语言模型推导上下文词表示时，需要决定如何为被切分为子词的未登录词（OOV）获取表示。用单个向量表示这些词的最佳方式是什么？这些表示的质量是否比已登录词的表示更差？我们在涉及未登录词的语义相似性任务上，对不同模型的嵌入进行了内在评估。我们的分析揭示了许多有趣的发现，其中之一是：被切分词的表示质量通常（但并非总是）比已知词嵌入的质量更差。然而，它们的相似度值必须谨慎解读。
英文摘要：
When deriving contextualized word representations from language models, a decision needs to be made on how to obtain one for out-of-vocabulary (OOV) words that are segmented into subwords. What is the best way to represent these words with a single vector, and are these representations of worse quality than those of in-vocabulary words? We carry out an intrinsic evaluation of embeddings from different models on semantic similarity tasks involving OOV words. Our analysis reveals, among other interesting findings, that the quality of representations of words that are split is often, but not always, worse than that of the embeddings of known words. Their similarity values, however, must be interpreted with caution.
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。
