Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userAlpha at SemEval-2021 Task 6: Transformer Based Propaganda Classification
ألفا في Semeval-2021 المهمة 6: تصنيف الدعاية القائمة
320
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تصف هذه الورقة نظامنا المشارك في المهمة 6 من Semeval-2021: تركز المهمة على تصنيف تقنية الدعاية متعددة الوسائط وتهدف إلى تصنيف الصورة والنص في 22 فئة. في هذه الورقة، نقترح استخدام الهندسة المعمارية القائمة على المحولات لفوسات القرائن من كل من الصورة والنص. نستكشف فرعين من التقنيات بما في ذلك ضبط النص المحول مسبقا مع ميزات مرئية ممتدة، وضبط المحولات مسبقا مسبقا. للحصول على الميزات المرئية، اختبرنا كل من ميزات الشبكة بناء على ميزات Resnet والمنطقة البارزة من كاشف كائن مسبقا. من بين المحولات متعددة الوسائط المسبدة مسبقا، نختار Ernie-Vil، وهو محولات من المحولات التي يحضرها اثنين من البخار المحددة على بيانات محاذاة على نطاق واسع على نطاق واسع. تنتج Ernie-Vil Fore-Tuing من أجل مهمتنا أداء أفضل بسبب التمثيل المتعدد الوسائط العام للنص والصورة التي تعلمتها إرني فيل. علاوة على ذلك، نظرا لأن توزيع ملصقات التصنيف غير متوازنة للغاية، فإننا نقوم أيضا بمحاولة أخرى على وظيفة الخسارة ويبلغ نتيجة التجربة أن فقدان البؤري سيؤدي أفضل من فقدان انتروبيا. أخيرا كنا فزنا أولا في Subtask C في المنافسة النهائية.
This paper describes our system participated in Task 6 of SemEval-2021: the task focuses on multimodal propaganda technique classification and it aims to classify given image and text into 22 classes. In this paper, we propose to use transformer based architecture to fuse the clues from both image and text. We explore two branches of techniques including fine-tuning the text pretrained transformer with extended visual features, and fine-tuning the multimodal pretrained transformers. For the visual features, we have tested both grid features based on ResNet and salient region features from pretrained object detector. Among the pretrained multimodal transformers, we choose ERNIE-ViL, a two-steam cross-attended transformers pretrained on large scale image-caption aligned data. Fine-tuing ERNIE-ViL for our task produce a better performance due to general joint multimodal representation for text and image learned by ERNIE-ViL. Besides, as the distribution of the classification labels is very unbalanced, we also make a further attempt on the loss function and the experiment result shows that focal loss would perform better than cross entropy loss. Last we have won first for subtask C in the final competition.
References used
https://aclanthology.org/
rate research
Read More
Among the tasks motivated by the proliferation of misinformation, propaganda detection is particularly challenging due to the deficit of fine-grained manual annotations required to train machine learning models. Here we show how data from other relat
ed tasks, including credibility assessment, can be leveraged in multi-task learning (MTL) framework to accelerate the training process. To that end, we design a BERT-based model with multiple output layers, train it in several MTL scenarios and perform evaluation against the SemEval gold standard.
We describe our systems of subtask1 and subtask3 for SemEval-2021 Task 6 on Detection of Persuasion Techniques in Texts and Images. The purpose of subtask1 is to identify propaganda techniques given textual content, and the goal of subtask3 is to det
ect them given both textual and visual content. For subtask1, we investigate transfer learning based on pre-trained language models (PLMs) such as BERT, RoBERTa to solve data sparsity problems. For subtask3, we extract heterogeneous visual representations (i.e., face features, OCR features, and multimodal representations) and explore various multimodal fusion strategies to combine the textual and visual representations. The official evaluation shows our ensemble model ranks 1st for subtask1 and 2nd for subtask3.
The objective of subtask 2 of SemEval-2021 Task 6 is to identify techniques used together with the span(s) of text covered by each technique. This paper describes the system and model we developed for the task. We first propose a pipeline system to i
dentify spans, then to classify the technique in the input sequence. But it severely suffers from handling the overlapping in nested span. Then we propose to formulize the task as a question answering task by MRC framework which achieves a better result compared to the pipeline method. Moreover, data augmentation and loss design techniques are also explored to alleviate the problem of data sparse and imbalance. Finally, we attain the 3rd place in the final evaluation phase.
This paper presents the solution proposed by the 1213Li team for subtask 3 in SemEval-2021 Task 6: identifying the multiple persuasion techniques used in the multi-modal content of the meme. We explored various approaches in feature extraction and th
e detection of persuasion labels. Our final model employs pre-trained models including RoBERTa and ResNet-50 as a feature extractor for texts and images, respectively, and adopts a label embedding layer with multi-modal attention mechanism to measure the similarity of labels with the multi-modal information and fuse features for label prediction. Our proposed method outperforms the provided baseline method and achieves 3rd out of 16 participants with 0.54860/0.22830 for Micro/Macro F1 scores.
This paper describes the system used by the AIMH Team to approach the SemEval Task 6. We propose an approach that relies on an architecture based on the transformer model to process multimodal content (text and images) in memes. Our architecture, cal
led DVTT (Double Visual Textual Transformer), approaches Subtasks 1 and 3 of Task 6 as multi-label classification problems, where the text and/or images of the meme are processed, and the probabilities of the presence of each possible persuasion technique are returned as a result. DVTT uses two complete networks of transformers that work on text and images that are mutually conditioned. One of the two modalities acts as the main one and the second one intervenes to enrich the first one, thus obtaining two distinct ways of operation. The two transformers outputs are merged by averaging the inferred probabilities for each possible label, and the overall network is trained end-to-end with a binary cross-entropy loss.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
