Lexical Semantic Recognition
Lexical Semantic Recognition
复制标题
DOI：
10.18653/v1/2021.mwe-1.6
复制
发表时间：
2020-04
期刊：
影响因子：
--
通讯作者：
Nelson F. Liu;Daniel Hershcovich;Michael Kranzlein;Nathan Schneider
中科院分区：
文献类型：
--
作者：
Nelson F. Liu;Daniel Hershcovich;Michael Kranzlein;Nathan Schneider
在词汇语义学中，尽管各种现象的整句切分和切分标注是相互依赖的，但它们通常是分开处理的。我们假设，一个统一的词汇语义识别任务是一种有效的方式来封装以前不同风格的注释，包括多词表达识别/分类和超义标记。使用STREUSLE语料库，我们训练了一个神经CRF序列标签，并评估其性能沿着各种轴的注释。由于标签集概括了以前的任务（PARSEME，DiMSUM），我们还评估了模型对这些测试集的概括程度，发现它接近或超过了现有的模型，尽管只在STREUSLE上进行了训练。我们的工作还建立了基准模型和评估指标的词汇语义的综合和准确的建模，促进在这一领域的未来工作。
In lexical semantics, full-sentence segmentation and segment labeling of various phenomena are generally treated separately, despite their interdependence. We hypothesize that a unified lexical semantic recognition task is an effective way to encapsulate previously disparate styles of annotation, including multiword expression identification / classification and supersense tagging. Using the STREUSLE corpus, we train a neural CRF sequence tagger and evaluate its performance along various axes of annotation. As the label set generalizes that of previous tasks (PARSEME, DiMSUM), we additionally evaluate how well the model generalizes to those test sets, finding that it approaches or surpasses existing models despite training only on STREUSLE. Our work also establishes baseline models and evaluation metrics for integrated and accurate modeling of lexical semantics, facilitating future work in this area.