Related papers: Dynamically Refined Regularization for Improving C…

Modern language modeling tasks are often underspecified: for a given token prediction, many words may satisfy the user's intent of producing natural language at inference time, however only one word will minimize the task's loss function at…

Hateful memes have emerged as a significant concern on the Internet. Detecting hateful memes requires the system to jointly understand the visual and textual modalities. Our investigation reveals that the embedding space of existing…

Automatic text-based diacritic restoration models generally have high diacritic error rates when applied to speech transcripts as a result of domain and style shifts in spoken language. In this work, we explore the possibility of improving…

Factual inconsistencies in generated summaries severely limit the practical applications of abstractive dialogue summarization. Although significant progress has been achieved by using pre-trained models, substantial amounts of hallucinated…

Social media platforms have recently seen an increase in the occurrence of hate speech discourse which has led to calls for improved detection methods. Most of these rely on annotated data, keywords, and a classification technique. While…

Offline handwriting recognition (HWR) has improved significantly with the advent of deep learning architectures in recent years. Nevertheless, it remains a challenging problem and practical applications often rely on post-processing…

Noise robustness in keyword spotting remains a challenge as many models fail to overcome the heavy influence of noises, causing the deterioration of the quality of feature embeddings. We proposed a contrastive regularization method called…

The performance of state-of-the-art neural rankers can deteriorate substantially when exposed to noisy inputs or applied to a new domain. In this paper, we present a novel method for fine-tuning neural rankers that can significantly improve…

Existing self-supervised learning strategies are constrained to either a limited set of objectives or generic downstream tasks that predominantly target uni-modal applications. This has isolated progress for imperative multi-modal…

Controllable text generation systems often leverage control codes to direct various properties of the output like style and length. Inspired by recent work on causal inference for NLP, this paper reveals a previously overlooked flaw in…

Hate speech, offensive language, aggression, racism, sexism, and other abusive language are common phenomena in social media. There is a need for Artificial Intelligence(AI)based intervention which can filter hate content at scale. Most…

Hate speech is a widespread and harmful form of online discourse, encompassing slurs and defamatory posts that can have serious social, psychological, and sometimes physical impacts on targeted individuals and communities. As social media…

Existing work on automated hate speech detection typically focuses on binary classification or on differentiating among a small set of categories. In this paper, we propose a novel method on a fine-grained hate speech classification task,…

Training a semantic segmentation model requires a large amount of pixel-level annotation, hampering its application at scale. With computer graphics, we can generate almost unlimited training data with precise annotation. However,a deep…

The proliferation of hate speech on social media platforms has necessitated the development of effective detection and moderation tools. This study evaluates the efficacy of various machine learning models in identifying hate speech and…

Language models are capable of iteratively improving their outputs based on natural language feedback, thus enabling in-context optimization of user preference. In place of human users, a second language model can be used as an evaluator,…

Hate speech annotation is costly, subjective, and prone to annotator disagreement, making large-scale dataset construction challenging. We systematically analyze how well large language models (LLMs) align with human judgments across ten…

In a hate speech detection model, we should consider two critical aspects in addition to detection performance-bias and explainability. Hate speech cannot be identified based solely on the presence of specific words: the model should be…

Natural language processing research has begun to embrace the notion of annotator subjectivity, motivated by variations in labelling. This approach understands each annotator's view as valid, which can be highly suitable for tasks that…

Trigger-word detection plays an important role as the entry point of user's communication with voice assistants. But supporting a particular word as a trigger-word involves huge amount of data collection, augmentation and labelling for that…