English
Related papers

Related papers: Exploring and Mitigating Gender Bias in Encoder-Ba…

200 papers

Word embeddings carry stereotypical connotations from the text they are trained on, which can lead to invalid inferences in downstream models that rely on them. We use this observation to design a mechanism for measuring stereotypes using…

Computation and Language · Computer Science 2019-11-27 Sunipa Dev , Tao Li , Jeff Phillips , Vivek Srikumar

Since 2017, the Transformer-based models play critical roles in various downstream Natural Language Processing tasks. However, a common limitation of the attention mechanism utilized in Transformer Encoder is that it cannot automatically…

Computation and Language · Computer Science 2022-04-20 Ziyang Luo , Yadong Xi , Jing Ma , Zhiwei Yang , Xiaoxi Mao , Changjie Fan , Rongsheng Zhang

In recent years, large Transformer-based Pre-trained Language Models (PLM) have changed the Natural Language Processing (NLP) landscape, by pushing the performance boundaries of the state-of-the-art on a wide variety of tasks. However, this…

Computation and Language · Computer Science 2024-01-15 Thibaud Leteno , Antoine Gourru , Charlotte Laclau , Christophe Gravier

Transformer models have shown impressive performance on a variety of NLP tasks. Off-the-shelf, pre-trained models can be fine-tuned for specific NLP classification tasks, reducing the need for large amounts of additional training data.…

Computation and Language · Computer Science 2020-10-06 Maaike Burghoorn , Maaike H. T. de Boer , Stephan Raaijmakers

Models based on the transformer architecture, such as BERT, have marked a crucial step forward in the field of Natural Language Processing. Importantly, they allow the creation of word embeddings that capture important semantic information…

Computation and Language · Computer Science 2021-01-01 Jacob Turton , David Vinson , Robert Elliott Smith

Institutional bias can impact patient outcomes, educational attainment, and legal system navigation. Written records often reflect bias, and once bias is identified; it is possible to refer individuals for training to reduce bias. Many…

This work describes experiments which probe the hidden representations of several BERT-style models for morphological content. The goal is to examine the extent to which discrete linguistic structure, in the form of morphological features…

Computation and Language · Computer Science 2020-04-08 Daniel Edmiston

Word vector representations are well developed tools for various NLP and Machine Learning tasks and are known to retain significant semantic and syntactic structure of languages. But they are prone to carrying and amplifying bias which can…

Computation and Language · Computer Science 2019-01-24 Sunipa Dev , Jeff Phillips

Neural Machine Translation systems built on top of Transformer-based architectures are routinely improving the state-of-the-art in translation quality according to word-overlap metrics. However, a growing number of studies also highlight…

Computation and Language · Computer Science 2022-10-18 Shanya Sharma , Manan Dey , Koustuv Sinha

We conduct a thorough study to diagnose the behaviors of pre-trained language encoders (ELMo, BERT, and RoBERTa) when confronted with natural grammatical errors. Specifically, we collect real grammatical errors from non-native speakers and…

Computation and Language · Computer Science 2020-05-13 Fan Yin , Quanyu Long , Tao Meng , Kai-Wei Chang

Large language models are becoming the go-to solution for the ever-growing number of tasks. However, with growing capacity, models are prone to rely on spurious correlations stemming from biases and stereotypes present in the training data.…

Computation and Language · Computer Science 2024-05-30 Tomasz Limisiewicz , David Mareček , Tomáš Musil

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 word embeddings…

Computation and Language · Computer Science 2019-04-19 Christine Basta , Marta R. Costa-jussà , Noe Casas

The pre-trained BERT model achieves a remarkable state of the art across a wide range of tasks in natural language processing. For solving the gender bias in gendered pronoun resolution task, I propose a novel neural network model based on…

Computation and Language · Computer Science 2019-08-02 Zili Wang

Encoder-only languages models are frequently used for a variety of standard machine learning tasks, including classification and retrieval. However, there has been a lack of recent research for encoder models, especially with respect to…

Computation and Language · Computer Science 2025-09-09 Marc Marone , Orion Weller , William Fleshman , Eugene Yang , Dawn Lawrie , Benjamin Van Durme

This paper studies gender bias in machine translation through the lens of Large Language Models (LLMs). Four widely-used test sets are employed to benchmark various base LLMs, comparing their translation quality and gender bias against…

Computation and Language · Computer Science 2024-07-29 Aleix Sant , Carlos Escolano , Audrey Mash , Francesca De Luca Fornaciari , Maite Melero

Large pre-trained language models are widely used in the community. These models are usually trained on unmoderated and unfiltered data from open sources like the Internet. Due to this, biases that we see in platforms online which are a…

Computation and Language · Computer Science 2023-04-17 Swapnil Sharma , Nikita Anand , Kranthi Kiran G. V. , Alind Jain

Classifiers tend to propagate biases present in the data on which they are trained. Hence, it is important to understand how the demographic identities of the annotators of comments affect the fairness of the resulting model. In this paper,…

Computation and Language · Computer Science 2021-06-07 Elizabeth Excell , Noura Al Moubayed

This paper presents exploratory work on whether and to what extent biases against queer and trans people are encoded in large language models (LLMs) such as BERT. We also propose a method for reducing these biases in downstream tasks:…

Computation and Language · Computer Science 2022-07-11 Virginia K. Felkner , Ho-Chun Herbert Chang , Eugene Jang , Jonathan May

The rapid growth of natural language processing (NLP) and pre-trained language models have enabled accurate text classification in a variety of settings. However, text classification models are susceptible to backdoor attacks, where an…

Cryptography and Security · Computer Science 2024-12-30 A. Dilara Yavuz , M. Emre Gursoy

Pre-training a transformer-based model for the language modeling task in a large dataset and then fine-tuning it for downstream tasks has been found very useful in recent years. One major advantage of such pre-trained language models is…

Computation and Language · Computer Science 2020-11-17 Md Tahmid Rahman Laskar , Enamul Hoque , Jimmy Xiangji Huang