论文标题
复杂单词识别的跨语性转移学习
Cross-Lingual Transfer Learning for Complex Word Identification
论文作者
论文摘要
复杂的单词识别（CWI）是一项任务，集中于在不同专业领域的文本中检测难以理解的单词或单词组。 CWI的目的是突出有问题的结构，这些结构通常很难理解。我们的方法使用零射击，一声和少量学习技术，以及最新的自然语言处理解决方案（NLP）任务（即变形金刚）。我们的目的是提供证据表明，拟议的模型可以通过依靠可用于四种不同语言的CWI共享任务2018数据集（即英语，德语，西班牙语和法语）来学习多种语言环境中复杂单词的特征。对于零拍学习方案，我们的方法在英语（0.774），德语（0.782）和西班牙语（0.734）语言方面超过了最先进的跨语性结果。同时，我们的模型还胜过德语（0.795宏观F1得分）的最新单语结果。
Complex Word Identification (CWI) is a task centered on detecting hard-to-understand words, or groups of words, in texts from different areas of expertise. The purpose of CWI is to highlight problematic structures that non-native speakers would usually find difficult to understand. Our approach uses zero-shot, one-shot, and few-shot learning techniques, alongside state-of-the-art solutions for Natural Language Processing (NLP) tasks (i.e., Transformers). Our aim is to provide evidence that the proposed models can learn the characteristics of complex words in a multilingual environment by relying on the CWI shared task 2018 dataset available for four different languages (i.e., English, German, Spanish, and also French). Our approach surpasses state-of-the-art cross-lingual results in terms of macro F1-score on English (0.774), German (0.782), and Spanish (0.734) languages, for the zero-shot learning scenario. At the same time, our model also outperforms the state-of-the-art monolingual result for German (0.795 macro F1-score).
