반응형 NLP572 [2023-12-22] 오늘의 자연어처리 HCDIR: End-to-end Hate Context Detection, and Intensity Reduction model for online comments Abstract:Warning: This paper contains examples of the language that some people may find offensive. Detecting and reducing hateful, abusive, offensive comments is a critical and challenging task on social media. Moreover, few studies aim to mitigate the intensity of hate speech. While studies have shown t.. 2023. 12. 22. [2023-12-21] 오늘의 자연어처리 Synergistic Anchored Contrastive Pre-training for Few-Shot Relation Extraction Abstract:Few-shot Relation Extraction (FSRE) aims to extract relational facts from a sparse set of labeled corpora. Recent studies have shown promising results in FSRE by employing Pre-trained Language Models (PLMs) within the framework of supervised contrastive learning, which considers both instances and label facts.. 2023. 12. 21. [2023-12-20] 오늘의 자연어처리 Efficiency-oriented approaches for self-supervised speech representation learning Abstract:Self-supervised learning enables the training of large neural models without the need for large, labeled datasets. It has been generating breakthroughs in several fields, including computer vision, natural language processing, biology, and speech. In particular, the state-of-the-art in several speech proce.. 2023. 12. 20. [2023-12-19] 오늘의 자연어처리 Data and Approaches for German Text simplification -- towards an Accessibility-enhanced Communication Abstract:This paper examines the current state-of-the-art of German text simplification, focusing on parallel and monolingual German corpora. It reviews neural language models for simplifying German texts and assesses their suitability for legal texts and accessibility requirements. Our findings.. 2023. 12. 19. 이전 1 ··· 3 4 5 6 7 8 9 ··· 143 다음 반응형