Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userNLP\_UIOWA at Semeval-2021 Task 5: Transferring Toxic Sets to Tag Toxic Spans
NLP \ _UIOWA في مهمة Semeval-2021 5: نقل مجموعات سامة إلى العلامة يمتد السامة
398
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
نستفيد من BLSTM مع الاهتمام لتحديد المواقف السامة في النصوص.نستكشف أبعاد مختلفة تؤثر على أداء النموذج.البعد الأول الذي تم استكشافه هو المجموعة السامة يتم تدريب النموذج.إلى جانب مجموعة البيانات المقدمة، نستكشف قدرة تحويل 5 مجموعات ذات صلة سامة مختلفة، بما في ذلك مجموعات الهجومية والسامة والمسيئة والكراهية.نجد أن المجموعة المسيئة فقط تظهر أعلى وعد القدرة على التحويل.البعد الثاني الذي نستكشفه هو المنهجية، بما في ذلك الاستفادة من الاهتمام، وتوظيف طريقة إزالة الجشع، باستخدام نسبة التردد، وفحص المجموعات الهجينة من طرق متعددة.نقوم بإجراء تحليل خطأ لفحص أنواع الأيوب السامة التي تم تفويتها والتي تم استنتاجها بشكل خاطئ على أنها سامة مع الأسباب الرئيسية وراء حدوثها.أخيرا، نقوم بتوسيع نطاق أسلوبنا عبر الفرع، والذي يحقق أعلى درجة F1 لدينا من 55.1.
We leverage a BLSTM with attention to identify toxic spans in texts. We explore different dimensions which affect the model's performance. The first dimension explored is the toxic set the model is trained on. Besides the provided dataset, we explore the transferability of 5 different toxic related sets, including offensive, toxic, abusive, and hate sets. We find that the solely offensive set shows the highest promise of transferability. The second dimension we explore is methodology, including leveraging attention, employing a greedy remove method, using a frequency ratio, and examining hybrid combinations of multiple methods. We conduct an error analysis to examine which types of toxic spans were missed and which were wrongly inferred as toxic along with the main reasons why they occurred. Finally, we extend our method via ensembles, which achieves our highest F1 score of 55.1.
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.
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.
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.
With the rapid growth in technology, social media activity has seen a boom across all age groups. It is humanly impossible to check all the tweets, comments and status manually whether they follow proper community guidelines. A lot of toxicity is reg
ularly posted on these social media platforms. This research aims to find toxic words in a sentence so that a healthy social community is built across the globe and the users receive censored content with specific warnings and facts. To solve this challenging problem, authors have combined concepts of Linked List for pre-processing and then used the idea of stacked embeddings like BERT Embeddings, Flair Embeddings and Word2Vec on the flairNLP framework to get the desired results. F1 metric was used to evaluate the model. The authors were able to produce a 0.74 F1 score on their test set.
Social network platforms are generally used to share positive, constructive, and insightful content. However, in recent times, people often get exposed to objectionable content like threat, identity attacks, hate speech, insults, obscene texts, offen
sive remarks or bullying. Existing work on toxic speech detection focuses on binary classification or on differentiating toxic speech among a small set of categories. This paper describes the system proposed by team Cisco for SemEval-2021 Task 5: Toxic Spans Detection, the first shared task focusing on detecting the spans in the text that attribute to its toxicity, in English language. We approach this problem primarily in two ways: a sequence tagging approach and a dependency parsing approach. In our sequence tagging approach we tag each token in a sentence under a particular tagging scheme. Our best performing architecture in this approach also proved to be our best performing architecture overall with an F1 score of 0.6922, thereby placing us 7th on the final evaluation phase leaderboard. We also explore a dependency parsing approach where we extract spans from the input sentence under the supervision of target span boundaries and rank our spans using a biaffine model. Finally, we also provide a detailed analysis of our results and model performance in our paper.
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
