Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userEntity at SemEval-2021 Task 5: Weakly Supervised Token Labelling for Toxic Spans Detection
كيان في Semeval-2021 المهمة 5: وضع علامة رمزية تحت الإشراف ضعيفا للكشف عن الأمور السامة
519
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
اكتشاف المواقف السامة - اكتشاف سمية المحتويات في حبيبتي الرموز - أمر حاسم للاعتدال الفعال للمناقشات عبر الإنترنت.تتمثل النهج الأساسي في هذه المشكلة في استخدام نموذج المحول في إضافة رأس تصنيف رمزي إلى طراز اللغة وضبط الطبقات الدقيقة مع مجموعة بيانات المسمى الرمز المميز.واحدة من قيود مثل هذا النهج الأساسي هي ندرة البيانات المسمى.لتحسين النتائج، درسنا الاستفادة من مجموعات البيانات العامة الحالية للحصول على مهمة ذات صلة ولكن مختلفة بتصنيف التعليق / الجملة بأكملها.نقترح مقارنتين: النهج الأول نماذج محول بخامة مدربة مسبقا في عينات تصنيف الجملة.في النهج الثاني، نقوم بإجراء إشراف ضعيف مع الاهتمام اللين لتعلم تسميات مستوى الرموز من ملصقات الجملة.تجاربنا تظهر التحسينات في درجة F1 عبر النهج الأساسي.تم إصدار التنفيذ علنا.
Detection of toxic spans - detecting toxicity of contents in the granularity of tokens - is crucial for effective moderation of online discussions. The baseline approach for this problem using the transformer model is to add a token classification head to the language model and fine-tune the layers with the token labeled dataset. One of the limitations of such a baseline approach is the scarcity of labeled data. To improve the results, We studied leveraging existing public datasets for a related but different task of entire comment/sentence classification. We propose two approaches: the first approach fine-tunes transformer models that are pre-trained on sentence classification samples. In the second approach, we perform weak supervision with soft attention to learn token level labels from sentence labels. Our experiments show improvements in the F1 score over the baseline approach. The implementation has been released publicly.
References used
https://aclanthology.org/
rate research
Read More
The Toxic Spans Detection task of SemEval-2021 required participants to predict the spans of toxic posts that were responsible for the toxic label of the posts. The task could be addressed as supervised sequence labeling, using training data with gol
d toxic spans provided by the organisers. It could also be treated as rationale extraction, using classifiers trained on potentially larger external datasets of posts manually annotated as toxic or not, without toxic span annotations. For the supervised sequence labeling approach and evaluation purposes, posts previously labeled as toxic were crowd-annotated for toxic spans. Participants submitted their predicted spans for a held-out test set and were scored using character-based F1. This overview summarises the work of the 36 teams that provided system descriptions.
In this work, we present our approach and findings for SemEval-2021 Task 5 - Toxic Spans Detection. The task's main aim was to identify spans to which a given text's toxicity could be attributed. The task is challenging mainly due to two constraints:
the small training dataset and imbalanced class distribution. Our paper investigates two techniques, semi-supervised learning and learning with Self-Adjusting Dice Loss, for tackling these challenges. Our submitted system (ranked ninth on the leader board) consisted of an ensemble of various pre-trained Transformer Language Models trained using either of the above-proposed techniques.
This paper presents our submission to SemEval-2021 Task 5: Toxic Spans Detection. The purpose of this task is to detect the spans that make a text toxic, which is a complex labour for several reasons. Firstly, because of the intrinsic subjectivity of
toxicity, and secondly, due to toxicity not always coming from single words like insults or offends, but sometimes from whole expressions formed by words that may not be toxic individually. Following this idea of focusing on both single words and multi-word expressions, we study the impact of using a multi-depth DistilBERT model, which uses embeddings from different layers to estimate the final per-token toxicity. Our quantitative results show that using information from multiple depths boosts the performance of the model. Finally, we also analyze our best model qualitatively.
This paper presents a system used for SemEval-2021 Task 5: Toxic Spans Detection. Our system is an ensemble of BERT-based models for binary word classification, trained on a dataset extended by toxic comments modified and generated by two language mo
dels. For the toxic word classification, the prediction threshold value was optimized separately for every comment, in order to maximize the expected F1 value.
In this paper, we describe our system used for SemEval 2021 Task 5: Toxic Spans Detection. Our proposed system approaches the problem as a token classification task. We trained our model to find toxic words and concatenate their spans to predict the
toxic spans within a sentence. We fine-tuned Pre-trained Language Models (PLMs) for identifying the toxic words. For fine-tuning, we stacked the classification layer on top of the PLM features of each word to classify if it is toxic or not. PLMs are pre-trained using different objectives and their performance may differ on downstream tasks. We, therefore, compare the performance of BERT, ELECTRA, RoBERTa, XLM-RoBERTa, T5, XLNet, and MPNet for identifying toxic spans within a sentence. Our best performing system used RoBERTa. It performed well, achieving an F1 score of 0.6841 and secured a rank of 16 on the official leaderboard.
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
