Search Results for author:
Found 46 papers, 7 papers with code
Extracting Age-Related Stereotypes from Social Media Texts
Age-related stereotypes are pervasive in our society, and yet have been under-studied in the NLP community.
Does Moral Code have a Moral Code? Probing Delphi’s Moral Philosophy
In an effort to guarantee that machine learning model outputs conform with human moral values, recent work has begun exploring the possibility of explicitly training models to learn the difference between right and wrong.
Concept-Based Explanations to Test for False Causal Relationships Learned by Abusive Language Classifiers
Classifiers tend to learn a false causal relationship between an over-represented concept and a label, which can result in over-reliance on the concept and compromised classification accuracy.
The crime of being poor
The criminalization of poverty has been widely denounced as a collective bias against the most vulnerable.
A Friendly Face: Do Text-to-Image Systems Rely on Stereotypes when the Input is Under-Specified?
As text-to-image systems continue to grow in popularity with the general public, questions have arisen about bias and diversity in the generated images.
Towards Procedural Fairness: Uncovering Biases in How a Toxic Language Classifier Uses Sentiment Information
For a multi-class toxic language classifier, we leverage a concept-based explanation framework to calculate the sensitivity of the model to the concept of sentiment, which has been used before as a salient feature for toxic language detection.
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
BIG-bench focuses on tasks that are believed to be beyond the capabilities of current language models.
Challenges in Applying Explainability Methods to Improve the Fairness of NLP Models
In this paper, we briefly review trends in explainability and fairness in NLP research, identify the current practices in which explainability methods are applied to detect and mitigate bias, and investigate the barriers preventing XAI methods from being used more widely in tackling fairness issues.
Explainable artificial intelligence
Explainable Artificial Intelligence (XAI)
+1
Does Moral Code Have a Moral Code? Probing Delphi's Moral Philosophy
In an effort to guarantee that machine learning model outputs conform with human moral values, recent work has begun exploring the possibility of explicitly training models to learn the difference between right and wrong.
Necessity and Sufficiency for Explaining Text Classifiers: A Case Study in Hate Speech Detection
We present a novel feature attribution method for explaining text classifiers, and analyze it in the context of hate speech detection.
Improving Generalizability in Implicitly Abusive Language Detection with Concept Activation Vectors
Robustness of machine learning models on ever-changing real-world data is critical, especially for applications affecting human well-being such as content moderation.
Understanding and Countering Stereotypes: A Computational Approach to the Stereotype Content Model
In this work, we present a computational approach to interpreting stereotypes in text through the Stereotype Content Model (SCM), a comprehensive causal theory from social psychology.
Confronting Abusive Language Online: A Survey from the Ethical and Human Rights Perspective
The pervasiveness of abusive content on the internet can lead to severe psychological and physical harm.
Towards Ethics by Design in Online Abusive Content Detection
To support safety and inclusion in online communications, significant efforts in NLP research have been put towards addressing the problem of abusive content detection, commonly defined as a supervised classification task.
On Cross-Dataset Generalization in Automatic Detection of Online Abuse
NLP research has attained high performances in abusive language detection as a supervised classification task.
SOLO: A Corpus of Tweets for Examining the State of Being Alone
We use SOLO to analyze the language and emotions associated with the state of being alone.
SemEval-2015 Task 10: Sentiment Analysis in Twitter
In this paper, we describe the 2015 iteration of the SemEval shared task on Sentiment Analysis in Twitter.
Big BiRD: A Large, Fine-Grained, Bigram Relatedness Dataset for Examining Semantic Composition
Finally, we present benchmark experiments on using the relatedness dataset as a testbed to evaluate simple unsupervised measures of semantic composition.
SemEval-2018 Task 1: Affect in Tweets
We present the SemEval-2018 Task 1: Affect in Tweets, which includes an array of subtasks on inferring the affectual state of a person from their tweet.
DeepMiner at SemEval-2018 Task 1: Emotion Intensity Recognition Using Deep Representation Learning
In this paper, we propose a regression system to infer the emotion intensity of a tweet.
Agree or Disagree: Predicting Judgments on Nuanced Assertions
Being able to predict whether people agree or disagree with an assertion (i. e. an explicit, self-contained statement) has several applications ranging from predicting how many people will like or dislike a social media post to classifying posts based on whether they are in accordance with a particular point of view.
NRC-Canada at SMM4H Shared Task: Classifying Tweets Mentioning Adverse Drug Reactions and Medication Intake
Our team, NRC-Canada, participated in two shared tasks at the AMIA-2017 Workshop on Social Media Mining for Health Applications (SMM4H): Task 1 - classification of tweets mentioning adverse drug reactions, and Task 2 - classification of tweets describing personal medication intake.
Examining Gender and Race Bias in Two Hundred Sentiment Analysis Systems
Automatic machine learning systems can inadvertently accentuate and perpetuate inappropriate human biases.
Sentiment Composition of Words with Opposing Polarities
In this paper, we explore sentiment composition in phrases that have at least one positive and at least one negative word---phrases like 'happy accident' and 'best winter break'.
The Effect of Negators, Modals, and Degree Adverbs on Sentiment Composition
Using phrasal terms in the created dataset, we analyze the impact of individual modifiers and the average effect of the groups of modifiers on overall sentiment.
Best-Worst Scaling More Reliable than Rating Scales: A Case Study on Sentiment Intensity Annotation
Rating scales are a widely used method for data annotation; however, they present several challenges, such as difficulty in maintaining inter- and intra-annotator consistency.
Capturing Reliable Fine-Grained Sentiment Associations by Crowdsourcing and Best-Worst Scaling
Access to word-sentiment associations is useful for many applications, including sentiment analysis, stance detection, and linguistic analysis.
Stance and Sentiment in Tweets
However, a person may express the same stance towards a target by using negative or positive language.
A Dataset for Detecting Stance in Tweets
Apart from stance, the tweets are also annotated for whether the target of interest is the target of opinion in the tweet.
Happy Accident: A Sentiment Composition Lexicon for Opposing Polarity Phrases
Sentiment composition is the determining of sentiment of a multi-word linguistic unit, such as a phrase or a sentence, based on its constituents.
Sentiment Lexicons for Arabic Social Media
Existing Arabic sentiment lexicons have low coverage―with only a few thousand entries.
Identifying Purpose Behind Electoral Tweets
Finally, we show that resources developed for emotion detection are also helpful for detecting purpose.
Using Nuances of Emotion to Identify Personality
Past work on personality detection has shown that frequency of lexical categories such as first person pronouns, past tense verbs, and sentiment words have significant correlations with personality traits.
NRC-Canada: Building the State-of-the-Art in Sentiment Analysis of Tweets
In this paper, we describe how we created two state-of-the-art SVM classifiers, one to detect the sentiment of messages such as tweets and SMS (message-level task) and one to detect the sentiment of a term within a submissions stood first in both tasks on tweets, obtaining an F-score of 69. 02 in the message-level task and 88. 93 in the term-level task.
Machine-learned solutions for three stages of clinical information extraction: the state of the art at i2b2 2010
Objective: As clinical text mining continues to mature, its potential as an enabling technology for innovations in patient care and clinical research is becoming a reality.
Ranked #5 on
Clinical Concept Extraction
on 2010 i2b2/VA
