Toxic comments contain forms of non-acceptable language targeted towards groups or individuals. These types of comments become a serious concern for government organizations, online communities, and social media platforms. Although there are some app
roaches to handle non-acceptable language, most of them focus on supervised learning and the English language. In this paper, we deal with toxic comment detection as a semi-supervised strategy over a heterogeneous graph. We evaluate the approach on a toxic dataset of the Portuguese language, outperforming several graph-based methods and achieving competitive results compared to transformer architectures.
This paper discusses different approaches to the Toxic Spans Detection task. The problem posed by the task was to determine which words contribute mostly to recognising a document as toxic. As opposed to binary classification of entire texts, word-le
vel assessment could be of great use during comment moderation, also allowing for a more in-depth comprehension of the model's predictions. As the main goal was to ensure transparency and understanding, this paper focuses on the current state-of-the-art approaches based on the explainable AI concepts and compares them to a supervised learning solution with word-level labels. The work consists of two xAI approaches that automatically provide the explanation for models trained for binary classification of toxic documents: an LSTM model with attention as a model-specific approach and the Shapley values for interpreting BERT predictions as a model-agnostic method. The competing approach considers this problem as supervised token classification, where models like BERT and its modifications were tested. The paper aims to explore, compare and assess the quality of predictions for different methods on the task. The advantages of each approach and further research direction are also discussed.
Toxicity is pervasive in social media and poses a major threat to the health of online communities. The recent introduction of pre-trained language models, which have achieved state-of-the-art results in many NLP tasks, has transformed the way in whi
ch we approach natural language processing. However, the inherent nature of pre-training means that they are unlikely to capture task-specific statistical information or learn domain-specific knowledge. Additionally, most implementations of these models typically do not employ conditional random fields, a method for simultaneous token classification. We show that these modifications can improve model performance on the Toxic Spans Detection task at SemEval-2021 to achieve a score within 4 percentage points of the top performing team.
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.
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.
Automatic detection of toxic language plays an essential role in protecting social media users, especially minority groups, from verbal abuse. However, biases toward some attributes, including gender, race, and dialect, exist in most training dataset
s for toxicity detection. The biases make the learned models unfair and can even exacerbate the marginalization of people. Considering that current debiasing methods for general natural language understanding tasks cannot effectively mitigate the biases in the toxicity detectors, we propose to use invariant rationalization (InvRat), a game-theoretic framework consisting of a rationale generator and a predictor, to rule out the spurious correlation of certain syntactic patterns (e.g., identity mentions, dialect) to toxicity labels. We empirically show that our method yields lower false positive rate in both lexical and dialectal attributes than previous debiasing methods.
With the ever-increasing availability of digital information, toxic content is also on the rise. Therefore, the detection of this type of language is of paramount importance. We tackle this problem utilizing a combination of a state-of-the-art pre-tr
ained language model (CharacterBERT) and a traditional bag-of-words technique. Since the content is full of toxic words that have not been written according to their dictionary spelling, attendance to individual characters is crucial. Therefore, we use CharacterBERT to extract features based on the word characters. It consists of a CharacterCNN module that learns character embeddings from the context. These are, then, fed into the well-known BERT architecture. The bag-of-words method, on the other hand, further improves upon that by making sure that some frequently used toxic words get labeled accordingly. With a ∼4 percent difference from the first team, our system ranked 36 th in the competition. The code is available for further research and reproduction of the results.
In recent years, the widespread use of social media has led to an increase in the generation of toxic and offensive content on online platforms. In response, social media platforms have worked on developing automatic detection methods and employing h
uman moderators to cope with this deluge of offensive content. While various state-of-the-art statistical models have been applied to detect toxic posts, there are only a few studies that focus on detecting the words or expressions that make a post offensive. This motivates the organization of the SemEval-2021 Task 5: Toxic Spans Detection competition, which has provided participants with a dataset containing toxic spans annotation in English posts. In this paper, we present the WLV-RIT entry for the SemEval-2021 Task 5. Our best performing neural transformer model achieves an 0.68 F1-Score. Furthermore, we develop an open-source framework for multilingual detection of offensive spans, i.e., MUDES, based on neural transformers that detect toxic spans in texts.
We study the task of labeling covert or veiled toxicity in online conversations. Prior research has highlighted the difficulty in creating language models that recognize nuanced toxicity such as microaggressions. Our investigations further underscore
the difficulty in parsing such labels reliably from raters via crowdsourcing. We introduce an initial dataset, COVERTTOXICITY, which aims to identify and categorize such comments from a refined rater template. Finally, we fine-tune a comment-domain BERT model to classify covertly offensive comments and compare against existing baselines.
