Since their inception, transformer-based language models have led to impressive performance gains across multiple natural language processing tasks. For Arabic, the current state-of-the-art results on most datasets are achieved by the AraBERT language model. Notwithstanding these recent advancements, sarcasm and sentiment detection persist to be challenging tasks in Arabic, given the language's rich morphology, linguistic disparity and dialectal variations. This paper proffers team SPPU-AASM's submission for the WANLP ArSarcasm shared-task 2021, which centers around the sarcasm and sentiment polarity detection of Arabic tweets. The study proposes a hybrid model, combining sentence representations from AraBERT with static word vectors trained on Arabic social media corpora. The proposed system achieves a F1-sarcastic score of 0.62 and a F-PN score of 0.715 for the sarcasm and sentiment detection tasks, respectively. Simulation results show that the proposed system outperforms multiple existing approaches for both the tasks, suggesting that the amalgamation of context-free and context-dependent text representations can help capture complementary facets of word meaning in Arabic. The system ranked second and tenth in the respective sub-tasks of sarcasm detection and sentiment identification.
CS-UM6P at SemEval-2022 Task 6: Transformer-based Models for Intended Sarcasm Detection in English and Arabic
Mohammed VI Polytechnic University(穆罕默德六世理工大学)
讽刺是比喻语言的一种形式,其中一个句子的预期含义与其字面意思不同。这对几个自然语言处理(NLP)应用(如情感分析、意见挖掘和作者分析)提出了严峻的挑战。在本文中,我们提出了我们的参与系统,在英语和阿拉伯语的预定讽刺检测任务。我们的系统\footnote{The source code of our system is available at \url{https://github.com/AbdelkaderMH/iSarcasmEval}}由三个基于深度学习的模型组成,利用了两个现有的阿拉伯语和英语的预训练语言模型。我们参与了所有的子任务。我们的正式提交在阿拉伯语的子任务A中表现最好,在子任务B中排名第二。对于子任务C,我们的系统在阿拉伯语和英语数据集上分别排名第7和第11位。
Domain-Adaptive Pre-Training for Arabic Aspect-Based Sentiment Analysis: A Comparative Study of Domain Adaptation and Fine-Tuning Strategies
Department of Computer Science, Faculty of Computing and Information Technology, King Abdulaziza University, Jeddah, Saudi Arabia(计算机科学系,计算与信息技术学院,国王阿卜杜勒阿齐兹大学,沙特阿拉伯吉达)
Zero-Resource Multi-Dialectal Arabic Natural Language Understanding
Cairo University(开罗大学)
需要合理数量的注释数据来微调下游任务上的预训练语言模型(PLM)。然而,获得不同语言变体的标记示例可能是昂贵的。在本文中,我们研究了仅在现代标准阿拉伯语(MSA)数据上微调PLM时对方言阿拉伯语(DA)的zero-shot性能-在DA上评估此类模型时发现显著的性能下降。为了弥补这种性能下降,我们提出了使用未标记的DA数据进行自训练,并将其应用于命名实体识别(NER),词性(POS)标记,和讽刺检测(SRD)。我们的研究结果证明了使用未标记DA数据进行自我训练的有效性:将zero-shot MSA到DA的转移提高了$\sim$ 10\% F $_1$(NER),2\%准确度(POS标记)和4.5\% F $_1$(SRD)。我们进行了一个消融实验,并表明直接观察到的性能提升结果来自用于自我训练的未标记DA示例。我们的工作为利用相对丰富的标记MSA数据集开发零资源和低资源方言的DA模型提供了机会。我们还报告了所有三项任务的最新性能,并为研究社区开放了我们的微调模型。