论文标题
与图形感知变压器的词汇配置的多语言提取和分类
Multilingual Extraction and Categorization of Lexical Collocations with Graph-aware Transformers
论文作者
论文摘要
在上下文中识别和分类词汇搭配对于语言学习，词典汇编和下游NLP有用。但是，由于冰冻度词汇搭配的不同程度，这是一项具有挑战性的任务。在本文中，我们提出了一个基于图形的变压器体系结构来增强基于BERT的模型的序列，我们对上下文中的搭配识别任务进行了评估。我们的结果表明，模型体系结构中明确编码句法依赖性是有帮助的，并提供了有关英语，西班牙语和法语中搭配典型典型差异的见解。
Recognizing and categorizing lexical collocations in context is useful for language learning, dictionary compilation and downstream NLP. However, it is a challenging task due to the varying degrees of frozenness lexical collocations exhibit. In this paper, we put forward a sequence tagging BERT-based model enhanced with a graph-aware transformer architecture, which we evaluate on the task of collocation recognition in context. Our results suggest that explicitly encoding syntactic dependencies in the model architecture is helpful, and provide insights on differences in collocation typification in English, Spanish and French.
