Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userSINAI at SemEval-2021 Task 5: Combining Embeddings in a BiLSTM-CRF model for Toxic Spans Detection
سيناء في مهمة Semeval-2021 5: الجمع بين المدينين في نموذج Bilstm-CRF للكشف عن الأمور السامة
279
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تصف هذه الورقة مشاركة فريق سيناء في المهمة 5: الكشف عن الأمور السامة التي تتكون من تحديد المواقف التي تجعل النص سام.على الرغم من أن العديد من الموارد والأنظمة قد تم تطويرها حتى الآن في سياق اللغة الهجومية، ركزت كل من التوضيحية والمهام بشكل رئيسي على تصنيف ما إذا كان النص مسيء أم لا.ومع ذلك، فإن اكتشاف المواقف السامة أمر بالغ الأهمية لتحديد سبب وجود نص سام ويمكنه مساعدة المشرفين البشري لتحديد موقع هذا النوع من المحتوى على وسائل التواصل الاجتماعي.من أجل إنجاز المهمة، نتبع نهجا عميقا قائم على التعلم باستخدام متغير ثنائي الاتجاه لشبكة ذاكرة طويلة الأجل طويلة إلى جانب طبقة فكري حقل عشوائية مشروطة (Bilstm-CRF).على وجه التحديد، نختبر أداء مزيج من مختلف تضمين الكلمة المدربة مسبقا للتعرف على الكيانات السامة في النص.تظهر النتائج أن مزيج من Adgeddings يساعد في اكتشاف المحتوى الهجومي.يرتب فريقنا 29 من أصل 91 مشاركا.
This paper describes the participation of SINAI team at Task 5: Toxic Spans Detection which consists of identifying spans that make a text toxic. Although several resources and systems have been developed so far in the context of offensive language, both annotation and tasks have mainly focused on classifying whether a text is offensive or not. However, detecting toxic spans is crucial to identify why a text is toxic and can assist human moderators to locate this type of content on social media. In order to accomplish the task, we follow a deep learning-based approach using a Bidirectional variant of a Long Short Term Memory network along with a stacked Conditional Random Field decoding layer (BiLSTM-CRF). Specifically, we test the performance of the combination of different pre-trained word embeddings for recognizing toxic entities in text. The results show that the combination of word embeddings helps in detecting offensive content. Our team ranks 29th out of 91 participants.
References used
https://aclanthology.org/
rate research
Read More
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.
Toxic language is often present in online forums, especially when politics and other polarizing topics arise, and can lead to people becoming discouraged from joining or continuing conversations. In this paper, we use data consisting of comments with
the indices of toxic text labelled to train an RNN to deter-mine which parts of the comments make them toxic, which could aid online moderators. We compare results using both the original dataset and an augmented set, as well as GRU versus LSTM RNN models.
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.
Detecting which parts of a sentence contribute to that sentence's toxicity---rather than providing a sentence-level verdict of hatefulness--- would increase the interpretability of models and allow human moderators to better understand the outputs of
the system. This paper presents our team's, UTNLP, methodology and results in the SemEval-2021 shared task 5 on toxic spans detection. We test multiple models and contextual embeddings and report the best setting out of all. The experiments start with keyword-based models and are followed by attention-based, named entity- based, transformers-based, and ensemble models. Our best approach, an ensemble model, achieves an F1 of 0.684 in the competition's evaluation phase.
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.
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
