语义还是拼写？用正字法噪声探测上下文词嵌入
Semantics or spelling? Probing contextual word embeddings with orthographic noise
AI总结：
通过向输入单词引入单字符交换的正字法噪声，发现预训练语言模型生成的上下文词嵌入对噪声高度敏感，且敏感性与子词分词相关，表明这些表示可能不是可靠的语义代理。
摘要：
预训练语言模型（PLM）的隐藏状态经常被用作上下文词嵌入（CWE）：即在给定语言上下文中编码语义信息的高维表示。在计算语言学研究的许多领域中，CWE之间的相似性被解释为语义相似性。然而，PLM隐藏状态中究竟编码了什么信息仍不清楚。我们通过使用最小的正字法噪声来探测PLM表示，以研究这一做法。我们预期，如果CWE主要编码语义信息，那么在给定足够语言上下文的情况下，输入单词中的单个字符交换不会显著影响所得到的表示。令人惊讶的是，我们发现由流行的PLM生成的CWE对输入数据中的噪声高度敏感，并且这种敏感性与子词分词有关：在输入中表示一个单词所用的token越少，其对应的CWE就越敏感。这表明CWE捕获了与词级意义无关的信息，并且可以通过对输入数据的微小修改来操纵。我们得出结论，这些由PLM派生的CWE可能不是可靠的语义代理，在解释表示相似性时需要谨慎。
英文摘要：
Pretrained language model (PLM) hidden states are frequently employed as contextual word embeddings (CWE): high-dimensional representations that encode semantic information given linguistic context. Across many areas of computational linguistics research, similarity between CWEs is interpreted as semantic similarity. However, it remains unclear exactly what information is encoded in PLM hidden states. We investigate this practice by probing PLM representations using minimal orthographic noise. We expect that if CWEs primarily encode semantic information, a single character swap in the input word will not drastically affect the resulting representation,given sufficient linguistic context. Surprisingly, we find that CWEs generated by popular PLMs are highly sensitive to noise in input data, and that this sensitivity is related to subword tokenization: the fewer tokens used to represent a word at input, the more sensitive its corresponding CWE. This suggests that CWEs capture information unrelated to word-level meaning and can be manipulated through trivial modifications of input data. We conclude that these PLM-derived CWEs may not be reliable semantic proxies, and that caution is warranted when interpreting representational similarity
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。
