Text classification is one of the most widely studied tasks in natural language processing. Motivated by the principle of compositionality, large multilayer neural network models have been employed for this task in an attempt to effectively utilize the constituent expressions. Almost all of the reported work train large networks using discriminative approaches, which come with a caveat of no proper capacity control, as they tend to latch on to any signal that may not generalize. Using various recent state-of-the-art approaches for text classification, we explore whether these models actually learn to compose the meaning of the sentences or still just focus on some keywords or lexicons for classifying the document. To test our hypothesis, we carefully construct datasets where the training and test splits have no direct overlap of such lexicons, but overall language structure would be similar. We study various text classifiers and observe that there is a big performance drop on these datasets. Finally, we show that even simple models with our proposed regularization techniques, which disincentivize focusing on key lexicons, can substantially improve classification accuracy.
Investigating the Influence of Prompt-Specific Shortcuts in AI Generated Text Detection
Seoul National University（首尔大学）；Hanyang University（汉阳大学）；Ewha Womans University（梨花女子大学）；NAVER Search US（NAVER美国搜索部门）；NAVER AI LAB（NAVER AI实验室）；NAVER Cloud（NAVER云）
Multilingual LAMA: Investigating Knowledge in Multilingual Pretrained Language Models
Center for Information and Language Processing (CIS), LMU Munich（慕尼黑大学信息与语言处理中心（CIS））
近年来，人们发现单语英语语言模型可以作为知识库。代替结构化知识库查询，使用诸如“Paris is the capital of [MASK]”之类的掩码语句作为探测。我们将已建立的基准TREx和GoogleRE翻译成53种语言。通过与mBERT合作，我们研究了三个问题。(i)mBERT可以用作多语言知识库吗？大多数以前的工作只考虑英语。将研究扩展到多种语言对于多样性和可访问性非常重要。(ii)mBERT作为知识库的性能是独立于语言的，还是因语言而异？(iii)多语言模型在更多文本上训练，例如，mBERT在104个维基百科上训练。mBERT能利用这一点来提高性能吗？我们发现，使用mBERT作为知识库会产生不同的语言和语言之间的池预测性能提高不同的性能。相反，mBERT表现出语言偏见;例如，当用意大利语查询时，它倾向于预测意大利是原产国。
Investigating an approach for low resource language dataset creation, curation and classification: Setswana and Sepedi
University of Pretoria（比勒陀利亚大学）；CSIR（科学与工业研究理事会）；University of Zululand（祖鲁兰大学）；University of Cape Town（开普敦大学）；University of Limpopo（林波波大学）；North-West University（西北大学）；University of the Witwatersrand（威特沃特斯兰德大学）
Investigating the Association Between Text-Based Indications of Foodborne Illness from Yelp Reviews and New York City Health Inspection Outcomes (2023)
Columbia University, Department of Computer Science（哥伦比亚大学计算机科学系）
