تشكل بروز أجهزة اللغة التصويرية، مثل السخرية والمفارقة، تحديات خطيرة لتحليل المعنويات العربية (SA).في حين أن أعمال البحث السابقة تعامل معها واكتشاف السخرية بشكل منفصل، تقدم هذه الورقة نموذجا للتعلم العميق المتعدد للمكملات المتعددة الإنهائية (MTL)، مما يتيح تفاعل المعرفة بين المهامتين.تتكون بنية MTL Model الخاصة بنا من تمثيل ترميز ثنائي الاتجاه من طراز المحولات (Bert)، وحدة تفاعل انتباه متعددة المهام، واثنين من مصنفين المهامين.تظهر النتائج الإجمالية التي تم الحصول عليها أن نموذجنا المقترح تتفوق على نظرائه المهمة الواحدة و MTL على كل من المهاجمة والشعور الفرعي للكشف عن المعنويات.
The prominence of figurative language devices, such as sarcasm and irony, poses serious challenges for Arabic Sentiment Analysis (SA). While previous research works tackle SA and sarcasm detection separately, this paper introduces an end-to-end deep Multi-Task Learning (MTL) model, allowing knowledge interaction between the two tasks. Our MTL model's architecture consists of a Bidirectional Encoder Representation from Transformers (BERT) model, a multi-task attention interaction module, and two task classifiers. The overall obtained results show that our proposed model outperforms its single-task and MTL counterparts on both sarcasm and sentiment detection subtasks.
References used
https://aclanthology.org/
Sarcasm detection and sentiment analysis are important tasks in Natural Language Understanding. Sarcasm is a type of expression where the sentiment polarity is flipped by an interfering factor. In this study, we exploited this relationship to enhance
We describe our submitted system to the 2021 Shared Task on Sarcasm and Sentiment Detection in Arabic (Abu Farha et al., 2021). We tackled both subtasks, namely Sarcasm Detection (Subtask 1) and Sentiment Analysis (Subtask 2). We used state-of-the-ar
Sentiment classification and sarcasm detection attract a lot of attention by the NLP research community. However, solving these two problems in Arabic and on the basis of social network data (i.e., Twitter) is still of lower interest. In this paper w
Sarcasm is one of the main challenges for sentiment analysis systems due to using implicit indirect phrasing for expressing opinions, especially in Arabic. This paper presents the system we submitted to the Sarcasm and Sentiment Detection task of WAN
Sarcasm detection is one of the top challenging tasks in text classification, particularly for informal Arabic with high syntactic and semantic ambiguity. We propose two systems that harness knowledge from multiple tasks to improve the performance of