Extracting legal entities from legal documents, particularly legal parties in contract documents, poses a significant challenge for legal assistive software. Many existing party extraction systems tend to generate numerous false positives due to the complex structure of the legal text. In this study, we present a novel and accurate method for extracting parties from legal contract documents by leveraging contextual span representations. To facilitate our approach, we have curated a large-scale dataset comprising 1000 contract documents with party annotations. Our method incorporates several enhancements to the SQuAD 2.0 question-answering system, specifically tailored to handle the intricate nature of the legal text. These enhancements include modifications to the activation function, an increased number of encoder layers, and the addition of normalization and dropout layers stacked on top of the output encoder layer. Baseline experiments reveal that our model, fine-tuned on our dataset, outperforms the current state-of-the-art model. Furthermore, we explore various combinations of the aforementioned techniques to further enhance the accuracy of our method. By employing a hybrid approach that combines 24 encoder layers with normalization and dropout layers, we achieve the best results, exhibiting an exact match score of 0.942 (+6.2% improvement).

Code-Mixed Offensive contents are used pervasively in social media posts in the last few years. Consequently, gained the significant attraction of the research community for identifying the different forms of such content (e.g., hate speech, and sentiments) and contributed to the creation of datasets. Most of the recent studies deal with high-resource languages (e.g., English) due to many publicly available datasets, and by the lack of dataset in low-resource anguages, those studies are slightly involved in these languages. Therefore, this study has the focus on offensive language identification on code-mixed low-resourced Dravidian languages such as Tamil, Kannada, and Malayalam using the bidirectional approach and fine-tuning strategies. According to the leaderboard, the proposed model got a 0.96 F1-score for Malayalam, 0.73 F1-score for Tamil, and 0.70 F1-score for Kannada in the bench-mark. Moreover, in the view of multilingual models, this modal ranked 3rd and achieved favorable results and confirmed the model as the best among all systems submitted to these shared tasks in these three languages.