Related papers: Gender Bias in Contextualized Word Embeddings
Black-box probing models can reliably extract linguistic features like tense, number, and syntactic role from pretrained word representations. However, the manner in which these features are encoded in representations remains poorly…
We present an empirical study of gender bias in coreference resolution systems. We first introduce a novel, Winograd schema-style set of minimal pair sentences that differ only by pronoun gender. With these "Winogender schemas," we evaluate…
Contextual language models (CLMs) have pushed the NLP benchmarks to a new height. It has become a new norm to utilize CLM provided word embeddings in downstream tasks such as text classification. However, unless addressed, CLMs are prone to…
The rapid growth of Speech Emotion Recognition (SER) has diverse global applications, from improving human-computer interactions to aiding mental health diagnostics. However, SER models might contain social bias toward gender, leading to…
Gender prediction has typically focused on lexical and social network features, yielding good performance, but making systems highly language-, topic-, and platform-dependent. Cross-lingual embeddings circumvent some of these limitations,…
With the starting point that implicit human biases are reflected in the statistical regularities of language, it is possible to measure biases in English static word embeddings. State-of-the-art neural language models generate dynamic word…
While understanding and removing gender biases in language models has been a long-standing problem in Natural Language Processing, prior research work has primarily been limited to English. In this work, we investigate some of the…
Word embeddings trained on large corpora have shown to encode high levels of unfair discriminatory gender, racial, religious and ethnic biases. In contrast, human-written dictionaries describe the meanings of words in a concise, objective…
Neural Machine Translation (NMT) models are state-of-the-art for machine translation. However, these models are known to have various social biases, especially gender bias. Most of the work on evaluating gender bias in NMT has focused…
State-of-the-art pretrained contextualized models (PCM) eg. BERT use tasks such as WiC and WSD to evaluate their word-in-context representations. This inherently assumes that performance in these tasks reflect how well a model represents…
Bias in word embeddings such as Word2Vec has been widely investigated, and many efforts made to remove such bias. We show how to use conceptors debiasing to post-process both traditional and contextualized word embeddings. Our conceptor…
We experiment with two recent contextualized word embedding methods (ELMo and BERT) in the context of open-domain argument search. For the first time, we show how to leverage the power of contextualized word embeddings to classify and…
Existing approaches to mitigate demographic biases evaluate on monolingual data, however, multilingual data has not been examined. In this work, we treat the gender as domains (e.g., male vs. female) and present a standard domain adaptation…
Vision-language models (VLMs) pre-trained on extensive datasets can inadvertently learn biases by correlating gender information with specific objects or scenarios. Current methods, which focus on modifying inputs and monitoring changes in…
We present a new approach for detecting human-like social biases in word embeddings using representational similarity analysis. Specifically, we probe contextualized and non-contextualized embeddings for evidence of intersectional biases…
The power of machine learning systems not only promises great technical progress, but risks societal harm. As a recent example, researchers have shown that popular word embedding algorithms exhibit stereotypical biases, such as gender bias.…
Neural Machine Translation (NMT) has been shown to struggle with grammatical gender that is dependent on the gender of human referents, which can cause gender bias effects. Many existing approaches to this problem seek to control gender…
Neural Machine Translation models tend to perpetuate gender bias present in their training data distribution. Context-aware models have been previously suggested as a means to mitigate this type of bias. In this work, we examine this claim…
Word embeddings use vectors to represent words such that the geometry between vectors captures semantic relationship between the words. In this paper, we develop a framework to demonstrate how the temporal dynamics of the embedding can be…
Training data for NLP tasks often exhibits gender bias in that fewer sentences refer to women than to men. In Neural Machine Translation (NMT) gender bias has been shown to reduce translation quality, particularly when the target language…