Abstract

The swift surge of digital communication on social media platforms has brought about an increase in hate speech online, especially sexism. Such content can have devastating effects on the psychological well-being of the users, and it becomes imperative to design automated systems that can identify and flag such harmful content. Human moderation alone is inadequate to manage the volume of content, necessitating efficient technological solutions. In this study, we explore the performance of different modern techniques on Bert-based models for detecting sexist text. We explore four such techniques, namely, Domain Adaptive Pre-training (DAP), Learning Rate Scheduling (LeR), Data Augmentation (DAug), and an ensemble of all three. The results show that each technique improves performance differently on each task due to their different approaches, which may be suited to a certain problem more. The ensemble model performs the best in all three subtasks. These models are trained on a Semeval’23 shared task dataset, which includes both sexist and non-sexist texts. All in all, this study explores the potential of DAP-LeR-DAug techniques in detecting sexist content. The results of this study highlight the strengths and weaknesses of the three different techniques with respect to each subtask. The results of this study will be useful for researchers and developers interested in developing systems for identifying and flagging online hate speech.

Abstract

No Results Found

Abstract

We present CoPara, the first publicly available paragraph-level (n-way aligned) multilingual parallel corpora for Dravidian languages. The collection contains 2856 paragraph/passage pairs between English and four Dravidian languages. We source the parallel paragraphs from the New India Samachar magazine and align them with English as a pivot language. We do human and artificial evaluations to validate the high-quality alignment and richness of the parallel paragraphs of a range of lengths. To show one of the many ways this dataset can be wielded, we finetuned IndicBART, an S2S transformer model on NMT for all XX-En pairs of languages in CoPara which perform better than existing sentence-level models on standard benchmarks (like BLEU) on sentence level translations and longer text too. We show how this dataset can enrich a model trained for a task like this, with more contextual cues and beyond sentence understanding even in low-resource settings like that of Dravidian languages. Finally, the dataset and models are made available publicly at GitHub to help advance research in Dravidian NLP, parallel multilingual, and beyond sentence-level tasks like NMT, etc.

Abstract

Subjective bias in Wikipedia textual data is a significant problem and affects millions of readers worldwide. Though some monolingual work has been done in classifying and debiasing biased text in resource-rich languages, the low-resource languages with large numbers of speakers remain unattended. We present an approach for the dual problems of multilingual bias detection and its mitigation with a thorough analysis. In this work, we establish competitive baselines on our preliminary approach, which includes classification-based modelling for bias detection on a multilingual dataset curated from existing monolingual sources. For the problem of bias mitigation, we follow the style transfer paradigm and model using transformer-based seq2seq architectures. We also discuss several approaches for further improvement in both problems as a part of our ongoing work.

Abstract

No Results Found

Abstract

This paper presents a method for automatically generating Wikipedia articles in the Hindi language, using Wikidata as a knowledge base. Our method extracts structured information from Wikidata, such as the names of entities, their properties, and their relationships, and then uses this information to generate natural language text that conforms to a set of templates designed for the domain of interest. We evaluate our method by generating articles about scientists, and we compare the resulting articles to machine-translated articles. Our results show that more than 70% of the generated articles using our method are better in terms of coherence, structure, and readability. Our approach has the potential to significantly reduce the time and effort required to create Wikipedia articles in Hindi and could be extended to other languages and domains as well.

Abstract

Document summarization aims to create a precise and coherent summary of a text document. Many deep learning summarization models are developed mainly for English, often requiring a large training corpus and efficient pre-trained language models and tools. However, English summarization models for low-resource Indian languages are often limited by rich morphological variation, syntax, and semantic differences. In this paper, we propose GAE-ISumm, an unsupervised Indic summarization model that extracts summaries from text documents. In particular, our proposed model, GAE-ISumm uses Graph Autoencoder (GAE) to learn text representations and a document summary jointly. We also provide a manually-annotated Telugu summarization dataset TELSUM, to experiment with our model GAE-ISumm. Further, we experiment with the most publicly available Indian language summarization datasets to investigate the effectiveness of GAE-ISumm on other Indian languages. Our experiments of GAE-ISumm in seven languages make the following observations: (i) it is competitive or better than state-of-the-art results on all datasets, (ii) it reports benchmark results on TELSUM, and (iii) the inclusion of positional and cluster information in the proposed model improved the performance of summaries.

Abstract

The rapid growth of online communication using social media platforms has led to an increase in the presence of hate speech, especially in terms of sexist language online. The proliferation of such hate speech has a significant impact on the mental health and well-being of the users and hence the need for automated systems to detect and filter such texts. In this study, we explore the effectiveness of conventional machine learning techniques for detecting sexist text. We explore five conventional classifiers, namely, Logistic Regression, Decision Tree, XGBoost, Support Vector Machines, and Random Forest. The results show that different classifiers perform differently on each task due to their different inherent architectures which may be suited to a certain problem more. These models are trained on the shared task dataset, which includes both sexist and non-sexist texts.All in all, this study explores the potential of conventional machine learning techniques in detecting online sexist content. The results of this study highlight the strengths and weaknesses of all classifiers with respect to all subtasks. The results of this study will be useful for researchers and practitioners interested in developing systems for detecting or filtering online hate speech.

Abstract

The Clickbait Spoiling shared task aims at tackling two aspects of spoiling: classifying the spoiler type based on its length and generating the spoiler. This paper focuses on the task of classifying the spoiler type. Better classification of the spoiler type would eventually help in generating a better spoiler for the post. We use BERT-base (cased) to classify the clickbait posts. The model achieves a balanced accuracy of 0.63 as we give only the post content as the input to our model instead of the concatenation of the post title and post content to find out the differences that the post title might be bringing in.

Abstract

The Clickbait Challenge targets spoiling the clickbaits using short pieces of information known as spoilers to satisfy the curiosity in- duced by a clickbait post. The large context of the article associated with the clickbait and differences in the spoiler forms, make the task challenging. Hence, to tackle the large con- text, we propose an Information Condensation- based approach, which prunes down the unnec- essary context. Given an article, our filtering module optimised with a contrastive learning objective first selects the parapraphs that are the most relevant to the corresponding clickbait. The resulting condensed article is then fed to the two downstream tasks of spoiler type clas- sification and spoiler generation. We demon- strate and analyze the gains from this approach on both the tasks. Overall, we win the task of spoiler type classification and achieve competi- tive results on spoiler generation