تعد التعميم المرتبطة مشكلة معروفة في الكشف عن الموقف (SD)، حيث تميل النظم إلى الأداء بشكل سيئ عند تعرضها للأهداف غير المرئية أثناء التدريب.بالنظر إلى أن شرح البيانات باهظ الثمن وتستغرق وقتا طويلا، فإن إيجاد طرق للاستفادة من البيانات غير المستقرة غير المسبقة يمكن أن تقدم فوائد كبيرة.في هذه الورقة، نطبق إطارا إشرافه ضعيفا لتعزيز التعميم الشامل من خلال البيانات المشروحة بتهمة التوحيد.نحن نركز على Twitter SD وإظهار تجريبيا من أن دمج البيانات الاصطناعية مفيدة للتعميم الشامل، مما يؤدي إلى تحسينات كبيرة في الأداء، مع المكاسب في درجات F1 تتراوح بين +3.4 إلى +5.1.
Cross-target generalization is a known problem in stance detection (SD), where systems tend to perform poorly when exposed to targets unseen during training. Given that data annotation is expensive and time-consuming, finding ways to leverage abundant unlabeled in-domain data can offer great benefits. In this paper, we apply a weakly supervised framework to enhance cross-target generalization through synthetically annotated data. We focus on Twitter SD and show experimentally that integrating synthetic data is helpful for cross-target generalization, leading to significant improvements in performance, with gains in F1 scores ranging from +3.4 to +5.1.
References used
https://aclanthology.org/
The goal of stance detection is to identify whether the author of a text is in favor of, neutral or against a specific target. Despite substantial progress on this task, one of the remaining challenges is the scarcity of annotations. Data augmentatio
Stance detection determines whether the author of a text is in favor of, against or neutral to a specific target and provides valuable insights into important events such as legalization of abortion. Despite significant progress on this task, one of
The 2020 US Elections have been, more than ever before, characterized by social media campaigns and mutual accusations. We investigate in this paper if this manifests also in online communication of the supporters of the candidates Biden and Trump, b
Multilingual language models exhibit better performance for some languages than for others (Singh et al., 2019), and many languages do not seem to benefit from multilingual sharing at all, presumably as a result of poor multilingual segmentation (Pyy
In this paper, we introduce a new English Twitter-based dataset for cyberbullying detection and online abuse. Comprising 62,587 tweets, this dataset was sourced from Twitter using specific query terms designed to retrieve tweets with high probabiliti