Frequency-based Distortions in Contextualized Word Embeddings
How does word frequency in pre-training data affect the behavior of similarity metrics in contextualized BERT embeddings? Are there systematic ways in which some word relationships are exaggerated or understated? In this work, we explore the geometric characteristics of contextualized word embeddings with two novel tools: (1) an identity probe that predicts the identity of a word using its embedding; (2) the minimal bounding sphere for a word's contextualized representations. Our results reveal that words of high and low frequency differ significantly with respect to their representational geometry. Such differences introduce distortions: when compared to human judgments, point estimates of embedding similarity (e.g., cosine similarity) can over- or under-estimate the semantic similarity of two words, depending on the frequency of those words in the training data. This has downstream societal implications: BERT-Base has more trouble differentiating between South American and African countries than North American and European ones. We find that these distortions persist when using BERT-Multilingual, suggesting that they cannot be easily fixed with additional data, which in turn introduces new distortions.
Code (0)
등록된 구현이 없습니다.
Tasks
Semantic SimilaritySemantic Textual SimilarityWord EmbeddingsMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
What Does This Word Mean? Explaining Contextualized Embeddings with Natural Language Definition
Contextualized word embeddings have boosted many NLP tasks compared with traditional static word embeddings. However, the word with a specific sense may have different contextualized embeddings due to its various context…
Word EmbeddingsDynamic Contextualized Word Embeddings
Static word embeddings that represent words by a single vector cannot capture the variability of word meaning in different linguistic and extralinguistic contexts. Building on prior work on contextualized and dynamic wor…
Language ModelingLanguage ModellingWord EmbeddingsKeyphrase Extraction from Scholarly Articles as Sequence Labeling using Contextualized Embeddings
In this paper, we formulate keyphrase extraction from scholarly articles as a sequence labeling task solved using a BiLSTM-CRF, where the words in the input text are represented using deep contextualized embeddings. We e…
ArticlesKeyphrase ExtractionWord EmbeddingsThe Role of Protected Class Word Lists in Bias Identification of Contextualized Word Representations
Systemic bias in word embeddings has been widely reported and studied, and efforts made to debias them; however, new contextualized embeddings such as ELMo and BERT are only now being similarly studied. Standard debiasin…
Word EmbeddingsEvaluating the Underlying Gender Bias in Contextualized Word Embeddings
Gender bias is highly impacting natural language processing applications. Word embeddings have clearly been proven both to keep and amplify gender biases that are present in current data sources. Recently, contextualized…
SentenceWord Embeddings