arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2104.11882cs.CL
收藏

基于多轮新类的增量式Few-Shot文本分类:公式、数据集和系统

Incremental Few-shot Text Classification with Multi-round New Classes: Formulation, Dataset and System

University of Illinois at Chicago(伊利诺伊大学芝加哥分校);Salesforce Research(赛富时研究院);University of Texas at Austin(德克萨斯大学奥斯汀分校)

Congying Xia, Wenpeng Yin, Yihao Feng, Philip Yu

摘要:

文本分类通常通过从预定义集合中用相关类别标记自然语言文本来研究。在现实世界中,新的类可能会不断挑战现有系统有限的标记数据。系统应该足够智能,能够通过一些示例识别即将到来的新类。在这项工作中,我们定义了一个新的任务在自然语言处理领域,增量Few-Shot文本分类,其中系统增量处理多轮的新类。对于每一轮,都有一批新的类,每个类都有一些标记的示例。在这个新的任务中存在两个主要的挑战:(i)对于学习过程,系统应该一轮一轮地递增地学习新的类,而不需要对先前类的示例进行重新训练;(ii)对于性能,系统应该在新类上表现良好,而不会对先前类造成太大损失。除了制定新任务外,我们还在增量Few-Shot设置中发布了两个基准数据集:意图分类和关系分类。此外,我们提出了两种蕴涵方法,ENTAILMENT和HYBRID,这表明解决这个新问题的承诺。

英文摘要:

Text classification is usually studied by labeling natural language texts with relevant categories from a predefined set. In the real world, new classes might keep challenging the existing system with limited labeled data. The system should be intelligent enough to recognize upcoming new classes with a few examples. In this work, we define a new task in the NLP domain, incremental few-shot text classification, where the system incrementally handles multiple rounds of new classes. For each round, there is a batch of new classes with a few labeled examples per class. Two major challenges exist in this new task: (i) For the learning process, the system should incrementally learn new classes round by round without re-training on the examples of preceding classes; (ii) For the performance, the system should perform well on new classes without much loss on preceding classes. In addition to formulating the new task, we also release two benchmark datasets in the incremental few-shot setting: intent classification and relation classification. Moreover, we propose two entailment approaches, ENTAILMENT and HYBRID, which show promise for solving this novel problem.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑