Spread Love Not Hate: Undermining the Importance of Hateful Pre-training for Hate Speech Detection

• URL: http://arxiv.org/abs/2210.04267v1
• Date: Sun, 9 Oct 2022 13:53:06 GMT
• Title: Spread Love Not Hate: Undermining the Importance of Hateful Pre-training for Hate Speech Detection
• Authors: Shantanu Patankar, Omkar Gokhale, Aditya Kane, Tanmay Chavan, Raviraj Joshi
• Abstract summary: We study the effects of hateful pre-training on low resource hate speech classification tasks. We evaluate different variations of tweet based BERT models pre-trained on hateful, non-hateful and mixed subsets of 40M tweet dataset. We show that pre-training on non-hateful text from target domain provides similar or better results.
• Score: 0.7874708385247353
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Pre-training large neural language models, such as BERT, has led to impressive gains on many natural language processing (NLP) tasks. Although this method has proven to be effective for many domains, it might not always provide desirable benefits. In this paper we study the effects of hateful pre-training on low resource hate speech classification tasks. While previous studies on English language have emphasized its importance, we aim to to augment their observations with some non-obvious insights. We evaluate different variations of tweet based BERT models pre-trained on hateful, non-hateful and mixed subsets of 40M tweet dataset. This evaluation is carried for Indian languages Hindi and Marathi. This paper is an empirical evidence that hateful pre-training is not the best pre-training option for hate speech detection. We show that pre-training on non-hateful text from target domain provides similar or better results. Further, we introduce HindTweetBERT and MahaTweetBERT, the first publicly available BERT models pre-trained on Hindi and Marathi tweets respectively. We show that they provide state-of-the-art performance on hate speech classification tasks. We also release a gold hate speech evaluation benchmark HateEval-Hi and HateEval-Mr consisting of manually labeled 2000 tweets each.

Related papers

• HCDIR: End-to-end Hate Context Detection, and Intensity Reduction model for online comments [2.162419921663162]
  We propose a novel end-to-end model, HCDIR, for Hate Context Detection, and Hate Intensity Reduction in social media posts. We fine-tuned several pre-trained language models to detect hateful comments to ascertain the best-performing hateful comments detection model.
  arXiv  Detail & Related papers  (2023-12-20T17:05:46Z)
• Harnessing Pre-Trained Sentence Transformers for Offensive Language Detection in Indian Languages [0.6526824510982802]
  This work delves into the domain of hate speech detection, placing specific emphasis on three low-resource Indian languages: Bengali, Assamese, and Gujarati. The challenge is framed as a text classification task, aimed at discerning whether a tweet contains offensive or non-offensive content. We fine-tuned pre-trained BERT and SBERT models to evaluate their effectiveness in identifying hate speech.
  arXiv  Detail & Related papers  (2023-10-03T17:53:09Z)
• Adversarial Training For Low-Resource Disfluency Correction [50.51901599433536]
  We propose an adversarially-trained sequence-tagging model for Disfluency Correction (DC) We show the benefit of our proposed technique, which crucially depends on synthetically generated disfluent data, by evaluating it for DC in three Indian languages. Our technique also performs well in removing stuttering disfluencies in ASR transcripts introduced by speech impairments.
  arXiv  Detail & Related papers  (2023-06-10T08:58:53Z)
• Overview of Abusive and Threatening Language Detection in Urdu at FIRE 2021 [50.591267188664666]
  We present two shared tasks of abusive and threatening language detection for the Urdu language. We present two manually annotated datasets containing tweets labelled as (i) Abusive and Non-Abusive, and (ii) Threatening and Non-Threatening. For both subtasks, m-Bert based transformer model showed the best performance.
  arXiv  Detail & Related papers  (2022-07-14T07:38:13Z)
• Addressing the Challenges of Cross-Lingual Hate Speech Detection [115.1352779982269]
  In this paper we focus on cross-lingual transfer learning to support hate speech detection in low-resource languages. We leverage cross-lingual word embeddings to train our neural network systems on the source language and apply it to the target language. We investigate the issue of label imbalance of hate speech datasets, since the high ratio of non-hate examples compared to hate examples often leads to low model performance.
  arXiv  Detail & Related papers  (2022-01-15T20:48:14Z)
• HS-BAN: A Benchmark Dataset of Social Media Comments for Hate Speech Detection in Bangla [2.055204980188575]
  In this paper, we present HS-BAN, a binary class hate speech dataset in Bangla language consisting of more than 50,000 labeled comments. We explore traditional linguistic features and neural network-based methods to develop a benchmark system for hate speech detection. Our benchmark shows that a Bi-LSTM model on top of the FastText informal word embedding achieved 86.78% F1-score.
  arXiv  Detail & Related papers  (2021-12-03T13:35:18Z)
• Ceasing hate withMoH: Hate Speech Detection in Hindi-English Code-Switched Language [2.9926023796813728]
  This work focuses on analyzing hate speech in Hindi-English code-switched language. To contain the structure of data, we developed MoH or Map Only Hindi, which means "Love" in Hindi. MoH pipeline consists of language identification, Roman to Devanagari Hindi transliteration using a knowledge base of Roman Hindi words.
  arXiv  Detail & Related papers  (2021-10-18T15:24:32Z)
• Understanding by Understanding Not: Modeling Negation in Language Models [81.21351681735973]
  Negation is a core construction in natural language. We propose to augment the language modeling objective with an unlikelihood objective that is based on negated generic sentences. We reduce the mean top1 error rate to 4% on the negated LAMA dataset.
  arXiv  Detail & Related papers  (2021-05-07T21:58:35Z)
• HASOCOne@FIRE-HASOC2020: Using BERT and Multilingual BERT models for Hate Speech Detection [9.23545668304066]
  We propose an approach to automatically classify hate speech and offensive content. We have used the datasets obtained from FIRE 2019 and 2020 shared tasks. We observed that the pre-trained BERT model and the multilingual-BERT model gave the best results.
  arXiv  Detail & Related papers  (2021-01-22T08:55:32Z)
• Emergent Communication Pretraining for Few-Shot Machine Translation [66.48990742411033]
  We pretrain neural networks via emergent communication from referential games. Our key assumption is that grounding communication on images---as a crude approximation of real-world environments---inductively biases the model towards learning natural languages.
  arXiv  Detail & Related papers  (2020-11-02T10:57:53Z)
• Kungfupanda at SemEval-2020 Task 12: BERT-Based Multi-Task Learning for Offensive Language Detection [55.445023584632175]
  We build an offensive language detection system, which combines multi-task learning with BERT-based models. Our model achieves 91.51% F1 score in English Sub-task A, which is comparable to the first place.
  arXiv  Detail & Related papers  (2020-04-28T11:27:24Z)

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.