English
Related papers

Related papers: Towards Equal Gender Representation in the Annotat…

200 papers

The task of image captioning implicitly involves gender identification. However, due to the gender bias in data, gender identification by an image captioning model suffers. Also, the gender-activity bias, owing to the word-by-word…

Computer Vision and Pattern Recognition · Computer Science 2019-12-03 Shruti Bhargava , David Forsyth

Many NLP tasks exhibit human label variation, where different annotators give different labels to the same texts. This variation is known to depend, at least in part, on the sociodemographics of annotators. Recent research aims to model…

Computation and Language · Computer Science 2025-03-03 Matthias Orlikowski , Paul Röttger , Philipp Cimiano , Dirk Hovy

The enormous amount of data being generated on the web and social media has increased the demand for detecting online hate speech. Detecting hate speech will reduce their negative impact and influence on others. A lot of effort in the…

Computation and Language · Computer Science 2021-11-03 Hind Saleh , Areej Alhothali , Kawthar Moria

Moderation is crucial to promoting healthy on-line discussions. Although several `toxicity' detection datasets and models have been published, most of them ignore the context of the posts, implicitly assuming that comments maybe judged…

Computation and Language · Computer Science 2020-06-02 John Pavlopoulos , Jeffrey Sorensen , Lucas Dixon , Nithum Thain , Ion Androutsopoulos

Automatic detection of toxic language plays an essential role in protecting social media users, especially minority groups, from verbal abuse. However, biases toward some attributes, including gender, race, and dialect, exist in most…

Computation and Language · Computer Science 2021-06-15 Yung-Sung Chuang , Mingye Gao , Hongyin Luo , James Glass , Hung-yi Lee , Yun-Nung Chen , Shang-Wen Li

Some users of social media are spreading racist, sexist, and otherwise hateful content. For the purpose of training a hate speech detection system, the reliability of the annotations is crucial, but there is no universally agreed-upon…

Computation and Language · Computer Science 2017-01-30 Björn Ross , Michael Rist , Guillermo Carbonell , Benjamin Cabrera , Nils Kurowsky , Michael Wojatzki

Large language models (LLMs) are increasingly used for automated text annotation in tasks ranging from academic research to content moderation and hiring. Across 19 LLMs and two experiments totaling more than 4 million annotation judgments,…

Computation and Language · Computer Science 2026-03-17 Petter Törnberg

Hate speech is an important problem in the management of user-generated content. To remove offensive content or ban misbehaving users, content moderators need reliable hate speech detectors. Recently, deep neural networks based on the…

Applications · Statistics 2020-12-18 Kristian Miok , Blaz Skrlj , Daniela Zaharie , Marko Robnik-Sikonja

Dialogue models trained on human conversations inadvertently learn to generate toxic responses. In addition to producing explicitly offensive utterances, these models can also implicitly insult a group or individual by aligning themselves…

Computation and Language · Computer Science 2021-09-14 Ashutosh Baheti , Maarten Sap , Alan Ritter , Mark Riedl

Demographics and cultural background of annotators influence the labels they assign in text annotation -- for instance, an elderly woman might find it offensive to read a message addressed to a "bro", but a male teenager might find it…

Toxic online speech has become a crucial problem nowadays due to an exponential increase in the use of internet by people from different cultures and educational backgrounds. Differentiating if a text message belongs to hate speech and…

Computation and Language · Computer Science 2021-08-24 Bencheng Wei , Jason Li , Ajay Gupta , Hafiza Umair , Atsu Vovor , Natalie Durzynski

Neural language models, which reach state-of-the-art results on most natural language processing tasks, are trained on large text corpora that inevitably contain value-burdened content and often capture undesirable biases, which the models…

Computation and Language · Computer Science 2024-03-21 Adnan Al Ali , Jindřich Libovický

Chemical named entity recognition (NER) models are used in many downstream tasks, from adverse drug reaction identification to pharmacoepidemiology. However, it is unknown whether these models work the same for everyone. Performance…

Computation and Language · Computer Science 2024-03-14 Xingmeng Zhao , Ali Niazi , Anthony Rios

Detecting and classifying instances of hate in social media text has been a problem of interest in Natural Language Processing in the recent years. Our work leverages state of the art Transformer language models to identify hate speech in a…

Computation and Language · Computer Science 2021-01-12 Sayar Ghosh Roy , Ujwal Narayan , Tathagata Raha , Zubair Abid , Vasudeva Varma

Many text corpora exhibit socially problematic biases, which can be propagated or amplified in the models trained on such data. For example, doctor cooccurs more frequently with male pronouns than female pronouns. In this study we (i)…

Computation and Language · Computer Science 2019-04-08 Shikha Bordia , Samuel R. Bowman

On social media platforms, hateful and offensive language negatively impact the mental well-being of users and the participation of people from diverse backgrounds. Automatic methods to detect offensive language have largely relied on…

Computation and Language · Computer Science 2022-01-26 Rishav Hada , Sohi Sudhir , Pushkar Mishra , Helen Yannakoudakis , Saif M. Mohammad , Ekaterina Shutova

Do LLMs align with human perceptions of safety? We study this question via annotation alignment, the extent to which LLMs and humans agree when annotating the safety of user-chatbot conversations. We leverage the recent DICES dataset (Aroyo…

Computation and Language · Computer Science 2024-10-08 Rajiv Movva , Pang Wei Koh , Emma Pierson

In this work, we examine the extent to which embeddings may encode marginalized populations differently, and how this may lead to a perpetuation of biases and worsened performance on clinical tasks. We pretrain deep embedding models (BERT)…

Computation and Language · Computer Science 2020-03-26 Haoran Zhang , Amy X. Lu , Mohamed Abdalla , Matthew McDermott , Marzyeh Ghassemi

Online harassment in the form of hate speech has been on the rise in recent years. Addressing the issue requires a combination of content moderation by people, aided by automatic detection methods. As content moderation is itself harmful to…

Computation and Language · Computer Science 2021-08-03 Sheikh Muhammad Sarwar , Vanessa Murdock

We introduce a simple yet efficient sentence-level attack on black-box toxicity detector models. By adding several positive words or sentences to the end of a hateful message, we are able to change the prediction of a neural network and…

Computation and Language · Computer Science 2023-10-23 Sergey Berezin , Reza Farahbakhsh , Noel Crespi