[go: up one dir, main page]
More Web Proxy on the site http://driver.im/

Aarthi S


2024

pdf bib
Bridging Numerical Reasoning and Headline Generation for Enhanced Language Models
Vaishnavi R | Srimathi T | Aarthi S | Harini V
Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)

Headline generation becomes a vital tool in the dynamic world of digital media, combining creativity and scientific rigor to engage readers while maintaining accuracy. However, accuracy is currently hampered by numerical integration problems, which affect both abstractive and extractive approaches. Sentences that are extracted from the original material are typically too short to accurately represent complex information. Our research introduces an innovative two-step training technique to tackle these problems, emphasizing the significance of enhanced numerical reasoning in headline development. Promising advances are presented by utilizing text-to-text processing capabilities of the T5 model and advanced NLP approaches like BERT and RoBERTa. With the help of external contributions and our dataset, our Flan-T5 model has been improved to demonstrate how these methods may be used to overcome numerical integration issues and improve the accuracy of headline production.

2023

pdf bib
CKingCoder at SemEval-2023 Task 9: Multilingual Tweet Intimacy Analysis
Harish B | Naveen D | Prem Balasubramanian | Aarthi S
Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)

The SemEval 2023 Task 9 Multilingual Tweet Intimacy Analysis, is a shared task for analysing the intimacy in the tweets posted on Twitter. The dataset was provided by Pei and Jurgens, who are part of the task organisers, for this task consists of tweets in various languages, such as Chinese, English, French, Italian, Portuguese, and Spanish. The testing dataset also had unseen languages such as Hindi, Arabic, Dutch and Korean. The tweets may or may not be related to intimacy. The task of our team was to score the intimacy in tweets and place it in the range of 05 based on the level of intimacy in the tweet using the dataset provided which consisted of tweets along with its scores. The intimacy score is used to indicate whether a tweet is intimate or not. Our team participated in the task and proposed the ROBERTa model to analyse the intimacy of the tweets.