paper-with-me

Papers

Frequency-based Distortions in Contextualized Word Embeddings

2021-04-17 · Kaitlyn Zhou, Kawin Ethayarajh, Dan Jurafsky

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.

📄 PDF Abstract BibTeX arXiv:2104.08465

Code (0)

등록된 구현이 없습니다.

Tasks

Semantic SimilaritySemantic Textual SimilarityWord Embeddings

Methods 이 논문이 사용한 방법론

American 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Adam 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Attention 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Similar Papers 제목 키워드 기반

What Does This Word Mean? Explaining Contextualized Embeddings with Natural Language Definition

2019-11-01 · IJCNLP 2019 11 · Ting-Yun Chang, Yun-Nung Chen

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 Embeddings

Dynamic Contextualized Word Embeddings

2020-10-23 · ACL 2021 5 · Valentin Hofmann, Janet B. Pierrehumbert, Hinrich Schütze

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 Embeddings

Keyphrase Extraction from Scholarly Articles as Sequence Labeling using Contextualized Embeddings

2019-10-19 · Dhruva Sahrawat, Debanjan Mahata, Mayank Kulkarni, Haimin Zhang 외

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 Embeddings

The Role of Protected Class Word Lists in Bias Identification of Contextualized Word Representations

2019-08-01 · WS 2019 8 · Jo{\~a}o Sedoc, Lyle Ungar

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 Embeddings

Evaluating the Underlying Gender Bias in Contextualized Word Embeddings

2019-04-18 · WS 2019 8 · Christine Basta, Marta R. Costa-jussà, Noe Casas

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