Related papers: Assessing Social and Intersectional Biases in Cont…

Societal bias towards certain communities is a big problem that affects a lot of machine learning systems. This work aims at addressing the racial bias present in many modern gender recognition systems. We learn race invariant…

Numerous works have analyzed biases in vision and pre-trained language models individually - however, less attention has been paid to how these biases interact in multimodal settings. This work extends text-based bias analysis methods to…

Word embeddings and convolutional neural networks (CNN) have attracted extensive attention in various classification tasks for Twitter, e.g. sentiment classification. However, the effect of the configuration used to train and generate the…

Gender-bias stereotypes have recently raised significant ethical concerns in natural language processing. However, progress in detection and evaluation of gender bias in natural language understanding through inference is limited and…

It is important for machines to interpret human emotions properly for better human-machine communications, as emotion is an essential part of human-to-human communications. One aspect of emotion is reflected in the language we use. How to…

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…

Natural Language Processing (NLP) has become increasingly utilized to provide adaptivity in educational applications. However, recent research has highlighted a variety of biases in pre-trained language models. While existing studies…

Text corpora are widely used resources for measuring societal biases and stereotypes. The common approach to measuring such biases using a corpus is by calculating the similarities between the embedding vector of a word (like nurse) and the…

As a step toward better document-level understanding, we explore classification of a sequence of sentences into their corresponding categories, a task that requires understanding sentences in context of the document. Recent successful…

Medical systems in general, and patient treatment decisions and outcomes in particular, are affected by bias based on gender and other demographic elements. As language models are increasingly applied to medicine, there is a growing…

Machine learning algorithms are extensively used to make increasingly more consequential decisions about people, so achieving optimal predictive performance can no longer be the only focus. A particularly important consideration is fairness…

With the growth of social medias, such as Twitter, plenty of user-generated data emerge daily. The short texts published on Twitter -- the tweets -- have earned significant attention as a rich source of information to guide many…

Language models encode and subsequently perpetuate harmful gendered stereotypes. Research has succeeded in mitigating some of these harms, e.g. by dissociating non-gendered terms such as occupations from gendered terms such as 'woman' and…

Word embeddings are a fixed, distributional representation of the context of words in a corpus learned from word co-occurrences. Despite their proven utility in machine learning tasks, word embedding models may capture uneven semantic and…

Idiomatic expressions can be problematic for natural language processing applications as their meaning cannot be inferred from their constituting words. A lack of successful methodological approaches and sufficiently large datasets prevents…

The neural architectures of language models are becoming increasingly complex, especially that of Transformers, based on the attention mechanism. Although their application to numerous natural language processing tasks has proven to be very…

Bipolar disorder is a chronic mental illness frequently underdiagnosed due to subtle early symptoms and social stigma. This paper explores the advanced natural language processing (NLP) models for recognizing signs of bipolar disorder based…

Several studies have been carried out on revealing linguistic features captured by BERT. This is usually achieved by training a diagnostic classifier on the representations obtained from different layers of BERT. The subsequent…

Static word embeddings encode word associations, extensively utilized in downstream NLP tasks. Although prior studies have discussed the nature of such word associations in terms of biases and lexical regularities captured, the variation in…

Semantic type mismatch between a noun and its context is central to coercion phenomena. This paper introduces a graph-based method to examine how lexical and contextual type information is reflected in word embeddings. We select nouns from…