论文标题
同时使用两个损失和两个数据集来提高尾流准确性
Using Two Losses and Two Datasets Simultaneously to Improve TempoWiC Accuracy
论文作者
论文摘要
WSD（单词sense删除）是识别文本或其他文本段中的单词意义的任务。研究人员已经从事这项任务（例如Pustejovsky，2002年）多年，但即使对于SOTA（最先进的）LMS（语言模型），它仍然具有挑战性。 Loureiro等人引入的新数据集，Tempowic。 （2022b）重点是单词随时间变化的事实。他们的最佳基线达到70.33％的宏观F1。在这项工作中，我们同时使用两种不同的损失来培训基于罗伯塔的分类模型。我们还通过使用另一个类似的数据集来改善模型来更好地概括。我们最好的配置将其最好的基线击败4.23％，并达到74.56％的Macrof1。
WSD (Word Sense Disambiguation) is the task of identifying which sense of a word is meant in a sentence or other segment of text. Researchers have worked on this task (e.g. Pustejovsky, 2002) for years but it's still a challenging one even for SOTA (state-of-the-art) LMs (language models). The new dataset, TempoWiC introduced by Loureiro et al. (2022b) focuses on the fact that words change over time. Their best baseline achieves 70.33% macro-F1. In this work, we use two different losses simultaneously to train RoBERTa-based classification models. We also improve our model by using another similar dataset to generalize better. Our best configuration beats their best baseline by 4.23% and reaches 74.56% macroF1.
