Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userLeCun at SemEval-2021 Task 6: Detecting Persuasion Techniques in Text Using Ensembled Pretrained Transformers and Data Augmentation
Lecun في Semeval-2021 Task 6: اكتشاف تقنيات الإقناع في نص باستخدام محولات محولات مسبقا حظرها وتعزيز البيانات
334
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
قمنا بتطوير نظام للمهمة 6 المهمة الفرعية 1 للكشف عن الدعاية في الميمات. تم استخدام مجموعة بيانات خارجية ومجموعة بيانات تكبير لتمديد مجموعة بيانات المنافسة الرسمية. تم تطبيق تقنيات تكبير البيانات على مجموعة البيانات الخارجية ومجموعة بيانات المنافسة للتوصل إلى مجموعة البيانات المعززة. تدربنا 5 محولات (Deberta و 4 روبرتا) وفرعهم لجعل التنبؤ. قمنا بتدريب نموذج 1 روبرتا في البداية على مجموعة البيانات المعززة لعدد قليل من العصر، ثم ضبطها على مجموعة بيانات المنافسة التي تحسن من النتائج F1 الصغرى حتى 0.1 درجات 0.1. بعد ذلك، تم تدريب نموذج روبرتا أولي آخر على مجموعة البيانات الخارجية، حيث تم دمجها مع مجموعة البيانات المعززة لعدد قليل من الحدوث والضبط بشكل جيد على مجموعة بيانات المنافسة. علاوة على ذلك، كنعت النماذج الأولية مع النماذج بعد ضبط الرصيد. بالنسبة للنموذج الأخير في الفرقة، قامنا بتدريب نموذج Deberta على مجموعة البيانات المعززة دون ضبطه على مجموعة بيانات المنافسة. أخيرا، بلغنا استرجاع إخراج كل نموذج في الفرقة لجعل التنبؤ.
We developed a system for task 6 sub-task 1 for detecting propaganda in memes. An external dataset and augmentation data-set were used to extend the official competition data-set. Data augmentation techniques were applied on the external data-set and competition data-set to come up with the augmented data-set. We trained 5 transformers (DeBERTa, and 4 RoBERTa) and ensembled them to make the prediction. We trained 1 RoBERTa model initially on the augmented data-set for a few epochs and then fine-tuned it on the competition data-set which improved the f1-micro up to 0.1 scores. After that, another initial RoBERTa model was trained on the external data-set merged with the augmented data-set for few epochs and fine-tuned it on the competition data-set. Furthermore, we ensembled the initial models with the models after fine-tuning. For the final model in the ensemble, we trained a DeBERTa model on the augmented data-set without fine-tuning it on the competition data-set. Finally, we averaged the output of each model in the ensemble to make the prediction.
References used
https://aclanthology.org/
rate research
Read More
This paper describes and examines different systems to address Task 6 of SemEval-2021: Detection of Persuasion Techniques In Texts And Images, Subtask 1. The task aims to build a model for identifying rhetorical and psycho- logical techniques (such a
s causal oversimplification, name-calling, smear) in the textual content of a meme which is often used in a disinformation campaign to influence the users. The paper provides an extensive comparison among various machine learning systems as a solution to the task. We elaborate on the pre-processing of the text data in favor of the task and present ways to overcome the class imbalance. The results show that fine-tuning a RoBERTa model gave the best results with an F1-Micro score of 0.51 on the development set.
We describe our approach for SemEval-2021 task 6 on detection of persuasion techniques in multimodal content (memes). Our system combines pretrained multimodal models (CLIP) and chained classifiers. Also, we propose to enrich the data by a data augmentation technique. Our submission achieves a rank of 8/16 in terms of F1-micro and 9/16 with F1-macro on the test set.
We describe SemEval-2021 task 6 on Detection of Persuasion Techniques in Texts and Images: the data, the annotation guidelines, the evaluation setup, the results, and the participating systems. The task focused on memes and had three subtasks: (i) de
tecting the techniques in the text, (ii) detecting the text spans where the techniques are used, and (iii) detecting techniques in the entire meme, i.e., both in the text and in the image. It was a popular task, attracting 71 registrations, and 22 teams that eventually made an official submission on the test set. The evaluation results for the third subtask confirmed the importance of both modalities, the text and the image. Moreover, some teams reported benefits when not just combining the two modalities, e.g., by using early or late fusion, but rather modeling the interaction between them in a joint model.
The following system description presents our approach to the detection of persuasion techniques in texts and images. The given task has been framed as a multi-label classification problem with the different techniques serving as class labels. The mu
lti-label classification problem is one in which a list of target variables such as our class labels is associated with every input chunk and assumes that a document can simultaneously and independently be assigned to multiple labels or classes. In order to assign class labels to the given memes, we opted for RoBERTa (A Robustly Optimized BERT Pretraining Approach) as a neural network architecture for token and sequence classification. Starting off with a pre-trained model for language representation we fine-tuned this model on the given classification task with the provided annotated data in supervised training steps. To incorporate image features in the multi-modal setting, we rely on the pre-trained VGG-16 model architecture.
In recent years, memes combining image and text have been widely used in social media, and memes are one of the most popular types of content used in online disinformation campaigns. In this paper, our study on the detection of persuasion techniques
in texts and images in SemEval-2021 Task 6 is summarized. For propaganda technology detection in text, we propose a combination model of both ALBERT and Text CNN for text classification, as well as a BERT-based multi-task sequence labeling model for propaganda technology coverage span detection. For the meme classification task involved in text understanding and visual feature extraction, we designed a parallel channel model divided into text and image channels. Our method achieved a good performance on subtasks 1 and 3. The micro F1-scores of 0.492, 0.091, and 0.446 achieved on the test sets of the three subtasks ranked 12th, 7th, and 11th, respectively, and all are higher than the baseline model.
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
