Search Results for author:
Found 32 papers, 18 papers with code
FEEL-IT: Emotion and Sentiment Classification for the Italian Language
While sentiment analysis is a popular task to understand people’s reactions online, we often need more nuanced information: is the post negative because the user is angry or sad?
XLM-EMO: Multilingual Emotion Prediction in Social Media Text
Detecting emotion in text allows social and computational scientists to study how people behave and react to online events.
MilaNLP @ WASSA: Does BERT Feel Sad When You Cry?
The paper describes the MilaNLP team’s submission (Bocconi University, Milan) in the WASSA 2021 Shared Task on Empathy Detection and Emotion Classification.
Measuring Harmful Sentence Completion in Language Models for LGBTQIA+ Individuals
Current language technology is ubiquitous and directly influences individuals’ lives worldwide.
Pipelines for Social Bias Testing of Large Language Models
We hope to open a discussion on the best methodologies to handle social bias testing in language models.
MilaNLP at SemEval-2022 Task 5: Using Perceiver IO for Detecting Misogynous Memes with Text and Image Modalities
In this paper, we describe the system proposed by the MilaNLP team for the Multimedia Automatic Misogyny Identification (MAMI) challenge.
HATE-ITA: New Baselines for Hate Speech Detection in Italian
Online hate speech is a dangerous phenomenon that can (and should) be promptly counteracted properly.
Benchmarking Post-Hoc Interpretability Approaches for Transformer-based Misogyny Detection
In this paper, we provide the first benchmark study of interpretability approaches for hate speech detection.
Which Matters Most? Comparing the Impact of Concept and Document Relationships in Topic Models
Topic models have been widely used to discover hidden topics in a collection of documents.
Nozza@LT-EDI-ACL2022: Ensemble Modeling for Homophobia and Transphobia Detection
In this paper, we describe our approach for the task of homophobia and transphobia detection in English social media comments.
FairBelief - Assessing Harmful Beliefs in Language Models
Language Models (LMs) have been shown to inherit undesired biases that might hurt minorities and underrepresented groups if such systems were integrated into real-world applications without careful fairness auditing.
A Tale of Pronouns: Interpretability Informs Gender Bias Mitigation for Fairer Instruction-Tuned Machine Translation
In MT, this might lead to misgendered translations, resulting, among other harms, in the perpetuation of stereotypes and prejudices.
Weigh Your Own Words: Improving Hate Speech Counter Narrative Generation via Attention Regularization
Regularized models produce better counter narratives than state-of-the-art approaches in most cases, both in terms of automatic metrics and human evaluation, especially when hateful targets are not present in the training data.
Wisdom of Instruction-Tuned Language Model Crowds. Exploring Model Label Variation
Recent studies emphasize the importance of considering human label variation in data annotation.
What about em? How Commercial Machine Translation Fails to Handle (Neo-)Pronouns
As 3rd-person pronoun usage shifts to include novel forms, e. g., neopronouns, we need more research on identity-inclusive NLP.
Measuring Harmful Representations in Scandinavian Language Models
Scandinavian countries are perceived as role-models when it comes to gender equality.
Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scale
For example, we find cases of prompting for basic traits or social roles resulting in images reinforcing whiteness as ideal, prompting for occupations resulting in amplification of racial and gender disparities, and prompting for objects resulting in reification of American norms.
Data-Efficient Strategies for Expanding Hate Speech Detection into Under-Resourced Languages
More data is needed, but annotating hateful content is expensive, time-consuming and potentially harmful to annotators.
The State of Profanity Obfuscation in Natural Language Processing
Work on hate speech has made the consideration of rude and harmful examples in scientific publications inevitable.
Is It Worth the (Environmental) Cost? Limited Evidence for Temporal Adaptation via Continuous Training
Consequently, we should continuously update our models with new data to expose them to new events and facts.
ferret: a Framework for Benchmarking Explainers on Transformers
With ferret, users can visualize and compare transformers-based models output explanations using state-of-the-art XAI methods on any free-text or existing XAI corpora.
Multilingual HateCheck: Functional Tests for Multilingual Hate Speech Detection Models
To help address this issue, we introduce Multilingual HateCheck (MHC), a suite of functional tests for multilingual hate speech detection models.
Entropy-based Attention Regularization Frees Unintended Bias Mitigation from Lists
EAR also reveals overfitting terms, i. e., terms most likely to induce bias, to help identify their effect on the model, task, and predictions.
Language Invariant Properties in Natural Language Processing
We introduce language invariant properties: i. e., properties that should not change when we transform text, and how they can be used to quantitatively evaluate the robustness of transformation algorithms.
Exposing the limits of Zero-shot Cross-lingual Hate Speech Detection
Reducing and counter-acting hate speech on Social Media is a significant concern.
HONEST: Measuring Hurtful Sentence Completion in Language Models
Our results show that 4. 3{\%} of the time, language models complete a sentence with a hurtful word.
Ranked #1 on
Hurtful Sentence Completion
on HONEST
Profiling Italian Misogynist: An Empirical Study
Hate speech may take different forms in online social environments.
Cross-lingual Contextualized Topic Models with Zero-shot Learning
They all cover the same content, but the linguistic differences make it impossible to use traditional, bag-of-word-based topic models.
What the [MASK]? Making Sense of Language-Specific BERT Models
Driven by the potential of BERT models, the NLP community has started to investigate and generate an abundant number of BERT models that are trained on a particular language, and tested on a specific data domain and task.
SemEval-2019 Task 5: Multilingual Detection of Hate Speech Against Immigrants and Women in Twitter
The paper describes the organization of the SemEval 2019 Task 5 about the detection of hate speech against immigrants and women in Spanish and English messages extracted from Twitter.
TWINE: A real-time system for TWeet analysis via INformation Extraction
In this paper we present TWINE, a real-time system for the big data analysis and exploration of information extracted from Twitter streams.
A Multi-View Sentiment Corpus
Sentiment Analysis is a broad task that involves the analysis of various aspect of the natural language text.
