Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userMultimodal or Text? Retrieval or BERT? Benchmarking Classifiers for the Shared Task on Hateful Memes
multimodal أو النص؟استرجاع أو بيرت؟معيار الطبقات للمهمة المشتركة على الميمات البغيضة
262
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
المهمة المشتركة بشأن الميمات البغيضة هي تحدي يهدف إلى اكتشاف المحتوى البغيض في الميمات من خلال دعوة تنفيذ النظم التي تفهم الميمات، يحتمل أن تجمع بين الصورة والمعلومات النصية.يتكون التحدي من ثلاثة مهام اكتشاف: الكراهية، الفئة المحمية ونوع الهجوم.الأول هو مهمة تصنيف ثنائية، في حين أن الاثنين الآخران مهام التصنيف متعدد العلامات.تضمنت مشاركتنا خط الأساس بيرت القائم على النص (TXTBERT)، وهو نفسه ولكن إضافة معلومات من الصورة (IMGBERT)، ونهج الاسترجاع العصبي.لقد جربنا أيضا نماذج التصنيف المعزز للاسترجاع.وجدنا أن مجموعة Txtbert و Imgbert تحقق أفضل أداء من حيث النتيجة AUC ROC في قسمين من المهام الثلاث في مجموعة التطوير الخاصة بنا.
The Shared Task on Hateful Memes is a challenge that aims at the detection of hateful content in memes by inviting the implementation of systems that understand memes, potentially by combining image and textual information. The challenge consists of three detection tasks: hate, protected category and attack type. The first is a binary classification task, while the other two are multi-label classification tasks. Our participation included a text-based BERT baseline (TxtBERT), the same but adding information from the image (ImgBERT), and neural retrieval approaches. We also experimented with retrieval augmented classification models. We found that an ensemble of TxtBERT and ImgBERT achieves the best performance in terms of ROC AUC score in two out of the three tasks on our development set.
References used
https://aclanthology.org/
rate research
Read More
Memes are the combinations of text and images that are often humorous in nature. But, that may not always be the case, and certain combinations of texts and images may depict hate, referred to as hateful memes. This work presents a multimodal pipelin
e that takes both visual and textual features from memes into account to (1) identify the protected category (e.g. race, sex etc.) that has been attacked; and (2) detect the type of attack (e.g. contempt, slurs etc.). Our pipeline uses state-of-the-art pre-trained visual and textual representations, followed by a simple logistic regression classifier. We employ our pipeline on the Hateful Memes Challenge dataset with additional newly created fine-grained labels for protected category and type of attack. Our best model achieves an AUROC of 0.96 for identifying the protected category, and 0.97 for detecting the type of attack. We release our code at https://github.com/harisbinzia/HatefulMemes
We present the results and main findings of the shared task at WOAH 5 on hateful memes detection. The task include two subtasks relating to distinct challenges in the fine-grained detection of hateful memes: (1) the protected category attacked by the
meme and (2) the attack type. 3 teams submitted system description papers. This shared task builds on the hateful memes detection task created by Facebook AI Research in 2020.
Hateful memes pose a unique challenge for current machine learning systems because their message is derived from both text- and visual-modalities. To this effect, Facebook released the Hateful Memes Challenge, a dataset of memes with pre-extracted te
xt captions, but it is unclear whether these synthetic examples generalize to memes in the wild'. In this paper, we collect hateful and non-hateful memes from Pinterest to evaluate out-of-sample performance on models pre-trained on the Facebook dataset. We find that memes in the wild' differ in two key aspects: 1) Captions must be extracted via OCR, injecting noise and diminishing performance of multimodal models, and 2) Memes are more diverse than traditional memes', including screenshots of conversations or text on a plain background. This paper thus serves as a reality-check for the current benchmark of hateful meme detection and its applicability for detecting real world hate.
This paper describes our submission (winning solution for Task A) to the Shared Task on Hateful Meme Detection at WOAH 2021. We build our system on top of a state-of-the-art system for binary hateful meme classification that already uses image tags s
uch as race, gender, and web entities. We add further metadata such as emotions and experiment with data augmentation techniques, as hateful instances are underrepresented in the data set.
The success of bidirectional encoders using masked language models, such as BERT, on numerous natural language processing tasks has prompted researchers to attempt to incorporate these pre-trained models into neural machine translation (NMT) systems.
However, proposed methods for incorporating pre-trained models are non-trivial and mainly focus on BERT, which lacks a comparison of the impact that other pre-trained models may have on translation performance. In this paper, we demonstrate that simply using the output (contextualized embeddings) of a tailored and suitable bilingual pre-trained language model (dubbed BiBERT) as the input of the NMT encoder achieves state-of-the-art translation performance. Moreover, we also propose a stochastic layer selection approach and a concept of a dual-directional translation model to ensure the sufficient utilization of contextualized embeddings. In the case of without using back translation, our best models achieve BLEU scores of 30.45 for En→De and 38.61 for De→En on the IWSLT'14 dataset, and 31.26 for En→De and 34.94 for De→En on the WMT'14 dataset, which exceeds all published numbers.
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
