12 accepted papers
In this paper, we propose Label-Aware Noise Elimination (LANE), a new approach that improves the robustness of deep learning models when trained under increased label noise in fine-grained text classification. LANE leverages the semantic relations between classes and monitors the training dynamics o…
Semi-supervised learning (SSL) has demonstrated high performance in image classification tasks by effectively utilizing both labeled and unlabeled data. However, existing SSL methods often suffer from poor calibration, with models yielding overconfident predictions that misrepresent actual predictio
Language models perform well on emotion datasets but it remains unclear whether these models indeed understand emotions expressed in text or simply exploit supperficial lexical cues (e.g., emotion words). In this paper, we present two novel test evaluation sets sourced from two existing datasets tha…
The debate surrounding gun control and gun regulation in the United States has intensified in the wake of numerous mass shooting events. As perspectives on this matter vary, it becomes increasingly important to comprehend individuals’ positions. Stance detection, the task of determining an author’s…
During natural disasters, people often use social media platforms such as Twitter to ask for help, to provide information about the disaster situation, or to express contempt about the unfolding event or public policies and guidelines. This contempt is in some cases expressed as sarcasm or irony. Un…
Automatically detecting emotions from text has countless applications, ranging from large scale opinion mining to social robots in healthcare and education. However, emotions are subjective in nature and are often expressed in ambiguous ways. At the same time, detecting emotions can also require imp…
We introduce MarginMatch, a new SSL approach combining consistency regularization and pseudo-labeling, with its main novelty arising from the use of unlabeled data training dynamics to measure pseudo-label quality. Instead of using only the model's confidence on an unlabeled example at an arbitrary…
Understanding what leads to emotions during large-scale crises is important as it can provide groundings for expressed emotions and subsequently improve the understanding of ongoing disasters. Recent approaches trained supervised models to both detect emotions and explain emotion triggers (events an…
The effectiveness of pre-trained language models in downstream tasks is highly dependent on the amount of labeled data available for training. Semi-supervised learning (SSL) is a promising technique that has seen wide attention recently due to its effectiveness in improving deep learning models when…
During natural disasters, people often use social media platforms, such as Twitter, to post information about casualties and damage produced by disasters. This information can help relief authorities gain situational awareness in nearly real time, and enable them to quickly distribute resources wher…
Crises such as the COVID-19 pandemic continuously threaten our world and emotionally affect billions of people worldwide in distinct ways. Understanding the triggers leading to people’s emotions is of crucial importance. Social media posts can be a good source of such analysis, yet these texts tend…
BERT has been shown to be extremely effective on a wide variety of natural language processing tasks, including sentiment analysis and emotion detection. However, the proposed pretraining objectives of BERT do not induce any sentiment or emotion-specific biases into the model. In this paper, we pres…