paper-with-me

Papers

When do Word Embeddings Accurately Reflect Surveys on our Beliefs About People?

2020-04-25 · ACL 2020 6 · Kenneth Joseph, Jonathan H. Morgan

Social biases are encoded in word embeddings. This presents a unique opportunity to study society historically and at scale, and a unique danger when embeddings are used in downstream applications. Here, we investigate the extent to which publicly-available word embeddings accurately reflect beliefs about certain kinds of people as measured via traditional survey methods. We find that biases found in word embeddings do, on average, closely mirror survey data across seventeen dimensions of social meaning. However, we also find that biases in embeddings are much more reflective of survey data for some dimensions of meaning (e.g. gender) than others (e.g. race), and that we can be highly confident that embedding-based measures reflect survey data only for the most salient biases.

📄 PDF Abstract BibTeX arXiv:2004.12043

Code (1)

kennyjoseph/embedding_impressions 공식 구현

Tasks

SurveyWord Embeddings

Similar Papers 제목 키워드 기반

SOS: Systematic Offensive Stereotyping Bias in Word Embeddings

2021-11-16 · ACL ARR September 2021 9 · Anonymous

Hate speech detection models aim to provide a safe environment for marginalised social groups to express themselves. However, the bias in these models could lead to silencing those groups. In this paper, we introduce the…

Hate Speech DetectionWord Embeddings

Exploring the Value of Personalized Word Embeddings

2020-11-11 · COLING 2020 8 · Charles Welch, Jonathan K. Kummerfeld, Verónica Pérez-Rosas, Rada Mihalcea

In this paper, we introduce personalized word embeddings, and examine their value for language modeling. We compare the performance of our proposed prediction model when using personalized versus generic word representat…

Authorship AttributionLanguage ModelingLanguage ModellingWord Embeddings

SOS: Systematic Offensive Stereotyping Bias in Word Embeddings

2022-10-01 · COLING 2022 10 · Fatma Elsafoury, Steve R. Wilson, Stamos Katsigiannis, Naeem Ramzan

Systematic Offensive stereotyping (SOS) in word embeddings could lead to associating marginalised groups with hate speech and profanity, which might lead to blocking and silencing those groups, especially on social media…

BlockingHate Speech DetectionWord Embeddings

Prediction is not Explanation: Revisiting the Explanatory Capacity of Mapping Embeddings

2025-08-19 · Hanna Herasimchyk, Alhassan Abdelhalim, Sören Laue, Michaela Regneri arxiv

Understanding what knowledge is implicitly encoded in deep learning models is essential for improving the interpretability of AI systems. This paper examines common methods to explain the knowledge encoded in word embedd…

Topology of Word Embeddings: Singularities Reflect Polysemy

2020-11-18 · Joint Conference on Lexical and Computational Semantics 2020 · Alexander Jakubowski, Milica Gašić, Marcus Zibrowius

The manifold hypothesis suggests that word vectors live on a submanifold within their ambient vector space. We argue that we should, more accurately, expect them to live on a pinched manifold: a singular quotient of a ma…

Word EmbeddingsWord Sense Induction