“文本分类任务作为自然语言处理领域的基础任务,在面向电信网络诈骗领域的案件分类中扮演着至关重要的角色,对于智能化案件分析具有重大意义和深远影响。本任务的目的是对给定案件描述文本进行分类,案件文本包含对案件的经过脱敏处理后的整体描述。我们首先采用Ernie预训练模型对案件内容进行微调的方法得到每个案件的类别,再使用伪标签和模型融合方法对目前的F1值进行提升,最终在CCL23-Eval任务6电信网络诈骗案件分类评测中取得第二名的成绩,该任务的评价指标F1值为0.8628,达到了较为先进的检测效果。”

We present Pixie, a manually annotated dataset for preference classification comprising 8,890 sentences drawn from app reviews. Unlike previous studies on preference classification, Pixie contains implicit (omitting an entity being compared) and indirect (lacking comparative linguistic cues) comparisons. We find that transformer-based pretrained models, finetuned on Pixie, achieve a weighted average F1 score of 83.34% and outperform the existing state-of-the-art preference classification model (73.99%).

Commitments and requests are a hallmark of collaborative communication, especially in team settings. Identifying specific tasks being committed to or request from emails and chat messages can enable important downstream tasks, such as producing todo lists, reminders, and calendar entries. State-of-the-art approaches for task identification rely on large annotated datasets, which are not always available, especially for domain-specific tasks. Accordingly, we propose Lin, an unsupervised approach of identifying tasks that leverages dependency parsing and VerbNet. Our evaluations show that Lin yields comparable or more accurate results than supervised models on domains with large training sets, and maintains its excellent performance on unseen domains.