نحن نصف نظامنا الذي تم تصنيفه في المرتبة الأولى في مهمة الكشف عن الكلام في الأمل (HSD) ورابعا في مهمة تشارك في الهجوم (OLI)، سواء في لغة التاميل.الهدف من HSD و OLI هو تحديد ما إذا كان تعليق أو منشور مختلط من التعليمات البرمجية يحتوي على خطاب نأمل أو محتوى مسيحي على التوالي.نقوم مسبقا بتدريب نموذج روبرتا المستندة إلى المحولات باستخدام البيانات المختلطة التي تم إنشاؤها بشكل عام واستخدامها في مجموعة جنبا إلى جنب مع نموذج Ulmfit المدرب مسبقا متاحا من Inltk.
We describe our system that ranked first in Hope Speech Detection (HSD) shared task and fourth in Offensive Language Identification (OLI) shared task, both in Tamil language. The goal of HSD and OLI is to identify if a code-mixed comment or post contains hope speech or offensive content respectively. We pre-train a transformer-based model RoBERTa using synthetically generated code-mixed data and use it in an ensemble along with their pre-trained ULMFiT model available from iNLTK.
References used
https://aclanthology.org/
In this paper, we describe our approach towards utilizing pre-trained models for the task of hope speech detection. We participated in Task 2: Hope Speech Detection for Equality, Diversity and Inclusion at LT-EDI-2021 @ EACL2021. The goal of this tas
This paper aims to describe the approach we used to detect hope speech in the HopeEDI dataset. We experimented with two approaches. In the first approach, we used contextual embeddings to train classifiers using logistic regression, random forest, SV
Analysis and deciphering code-mixed data is imperative in academia and industry, in a multilingual country like India, in order to solve problems apropos Natural Language Processing. This paper proposes a bidirectional long short-term memory (BiLSTM)
In today's society, the rapid development of communication technology allows us to communicate with people from different parts of the world. In the process of communication, each person treats others differently. Some people are used to using offens
Hope is an essential aspect of mental health stability and recovery in every individual in this fast-changing world. Any tools and methods developed for detection, analysis, and generation of hope speech will be beneficial. In this paper, we propose