Semantics or spelling? Probing contextual word embeddings with orthographic noise
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
Code (1)
Tasks
Language ModelingLanguage ModellingSemantic SimilaritySemantic Textual SimilarityWord EmbeddingsSimilar Papers 제목 키워드 기반
Spying on your neighbors: Fine-grained probing of contextual embeddings for information about surrounding words
Although models using contextual word embeddings have achieved state-of-the-art results on a host of NLP tasks, little is known about exactly what information these embeddings encode about the context words that they are…
Word EmbeddingsDo Word Embeddings Capture Spelling Variation?
Analyses of word embeddings have primarily focused on semantic and syntactic properties. However, word embeddings have the potential to encode other properties as well. In this paper, we propose a new perspective on the …
Word EmbeddingsMisspelling Correction with Pre-trained Contextual Language Model
Spelling irregularities, known now as spelling mistakes, have been found for several centuries. As humans, we are able to understand most of the misspelled words based on their location in the sentence, perceived pronunc…
Language ModelingLanguage ModellingSentenceSpelling Correction+1Conditional probing: measuring usable information beyond a baseline
Probing experiments investigate the extent to which neural representations make properties -- like part-of-speech -- predictable. One suggests that a representation encodes a property if probing that representation produ…
Word EmbeddingsMisspelling Oblivious Word Embeddings
In this paper we present a method to learn word embeddings that are resilient to misspellings. Existing word embeddings have limited applicability to malformed texts, which contain a non-negligible amount of out-of-vocab…
Word Embeddings