IITK@Detox at SemEval-2021 Task 5: Semi-Supervised Learning and Dice
Loss for Toxic Spans Detection
- URL: http://arxiv.org/abs/2104.01566v1
- Date: Sun, 4 Apr 2021 08:39:55 GMT
- Title: IITK@Detox at SemEval-2021 Task 5: Semi-Supervised Learning and Dice
Loss for Toxic Spans Detection
- Authors: Archit Bansal, Abhay Kaushik, Ashutosh Modi
- Abstract summary: 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.
Our paper investigates two techniques, semi-supervised learning and learning with Self-Adjusting Dice Loss, for tackling these challenges.
- Score: 2.1012672709024294
- License: http://creativecommons.org/licenses/by-nc-sa/4.0/
- Abstract: 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.
Related papers
- Strategies to Harness the Transformers' Potential: UNSL at eRisk 2023 [0.9208007322096532]
The CLEF eRisk Laboratory explores solutions to different tasks related to risk detection on the Internet.
In the 2023 edition, Task 1 consisted of searching for symptoms of depression, the objective of which was to extract user writings according to their relevance to the BDI Questionnaire symptoms.
Task 2 was related to the problem of early detection of pathological gambling risks, where the participants had to detect users at risk as quickly as possible.
Task 3 consisted of estimating the severity levels of signs of eating disorders.
arXiv Detail & Related papers (2023-10-30T19:34:33Z) - Adding Instructions during Pretraining: Effective Way of Controlling
Toxicity in Language Models [29.505176809305095]
We propose two novel pretraining data augmentation strategies that significantly reduce model toxicity without compromising its utility.
Our two strategies are: (1) MEDA: adds raw toxicity score as meta-data to the pretraining samples, and (2) INST: adds instructions to those samples indicating their toxicity.
Our results indicate that our best performing strategy (INST) substantially reduces the toxicity probability up to 61% while preserving the accuracy on five benchmark NLP tasks.
arXiv Detail & Related papers (2023-02-14T23:00:42Z) - Effective Cross-Task Transfer Learning for Explainable Natural Language
Inference with T5 [50.574918785575655]
We compare sequential fine-tuning with a model for multi-task learning in the context of boosting performance on two tasks.
Our results show that while sequential multi-task learning can be tuned to be good at the first of two target tasks, it performs less well on the second and additionally struggles with overfitting.
arXiv Detail & Related papers (2022-10-31T13:26:08Z) - Combining Modular Skills in Multitask Learning [149.8001096811708]
A modular design encourages neural models to disentangle and recombine different facets of knowledge to generalise more systematically to new tasks.
In this work, we assume each task is associated with a subset of latent discrete skills from a (potentially small) inventory.
We find that the modular design of a network significantly increases sample efficiency in reinforcement learning and few-shot generalisation in supervised learning.
arXiv Detail & Related papers (2022-02-28T16:07:19Z) - Active Multi-Task Representation Learning [50.13453053304159]
We give the first formal study on resource task sampling by leveraging the techniques from active learning.
We propose an algorithm that iteratively estimates the relevance of each source task to the target task and samples from each source task based on the estimated relevance.
arXiv Detail & Related papers (2022-02-02T08:23:24Z) - UoB at SemEval-2021 Task 5: Extending Pre-Trained Language Models to
Include Task and Domain-Specific Information for Toxic Span Prediction [0.8376091455761259]
Toxicity is pervasive in social media and poses a major threat to the health of online communities.
Recent introduction of pre-trained language models, which have achieved state-of-the-art results in many NLP tasks, has transformed the way in which we approach natural language processing.
arXiv Detail & Related papers (2021-10-07T18:29:06Z) - Two-Stream Consensus Network: Submission to HACS Challenge 2021
Weakly-Supervised Learning Track [78.64815984927425]
The goal of weakly-supervised temporal action localization is to temporally locate and classify action of interest in untrimmed videos.
We adopt the two-stream consensus network (TSCN) as the main framework in this challenge.
Our solution ranked 2rd in this challenge, and we hope our method can serve as a baseline for future academic research.
arXiv Detail & Related papers (2021-06-21T03:36:36Z) - UPB at SemEval-2021 Task 5: Virtual Adversarial Training for Toxic Spans
Detection [0.7197592390105455]
Semeval-2021, Task 5 - Toxic Spans Detection is based on a novel annotation of a subset of the Jigsaw Unintended Bias dataset.
For this task, participants had to automatically detect character spans in short comments that render the message as toxic.
Our model considers applying Virtual Adversarial Training in a semi-supervised setting during the fine-tuning process of several Transformer-based models.
arXiv Detail & Related papers (2021-04-17T19:42:12Z) - WLV-RIT at SemEval-2021 Task 5: A Neural Transformer Framework for
Detecting Toxic Spans [2.4737119633827174]
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.
Social media platforms have worked on developing automatic detection methods and employing human moderators to cope with this deluge of offensive content.
arXiv Detail & Related papers (2021-04-09T22:52:26Z) - Few-shot Action Recognition with Prototype-centered Attentive Learning [88.10852114988829]
Prototype-centered Attentive Learning (PAL) model composed of two novel components.
First, a prototype-centered contrastive learning loss is introduced to complement the conventional query-centered learning objective.
Second, PAL integrates a attentive hybrid learning mechanism that can minimize the negative impacts of outliers.
arXiv Detail & Related papers (2021-01-20T11:48:12Z) - Incremental Embedding Learning via Zero-Shot Translation [65.94349068508863]
Current state-of-the-art incremental learning methods tackle catastrophic forgetting problem in traditional classification networks.
We propose a novel class-incremental method for embedding network, named as zero-shot translation class-incremental method (ZSTCI)
In addition, ZSTCI can easily be combined with existing regularization-based incremental learning methods to further improve performance of embedding networks.
arXiv Detail & Related papers (2020-12-31T08:21:37Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.