← Search

Aaditya Bodke

2 accepted papers

2025

ERU-KG: Efficient Reference-aligned Unsupervised Keyphrase Generation

ACL 2025long

Unsupervised keyphrase prediction has gained growing interest in recent years. However, existing methods typically rely on heuristically defined importance scores, which may lead to inaccurate informativeness estimation. In addition, they lack consideration for time efficiency. To solve these proble…

2025

PASTEL : Polarity-Aware Sentiment Triplet Extraction with LLM-as-a-Judge

ACL 2025finding

Aspect Sentiment Triplet Extraction (ASTE) is a subtask of Aspect-Based Sentiment Analysis (ABSA) that aims to extract aspect terms, corresponding opinion terms, and their associated sentiment polarities from text. Current end-to-end approaches, whether employing Large Language Models (LLMs) or comp…

Cited by 0SourcePDFScholar