DIAL 연구실 소속 인공지능학과 최은성(석·박통합과정, 제1저자) 학생, 이혜리(석·박통합과정, 제2저자) 학생, 이종욱(교신저자) 교수가 참여한 “Multi-Granularity Guided Fusion-in-Decoder” 논문이 자연어처리 분야 최우수 국제 학술대회인 Findings of the 2024 Annual Conference of the North American Chapter of the Association for Computational Linguistics (Findings of NAACL)에 최종 게재가 승인되었으며 오는 6월에 발표될 예정입니다.

Abstract

In Open-domain Question Answering (ODQA), it is essential to effectively discern relevant contexts as evidence and avoid ambiguous and spurious ones from retrieved results. To address this, we propose the Multi-Granularity guided Fusion-in-Decoder (MGFiD), discerning evidence across multiple levels of granularity. Based on multi-task learning, MGFiD harmonizes passage re-ranking with sentence classification. It aggregates evident sentences into an anchor vector that instructs the decoder. Additionally, it improves decoding efficiency by reusing the results of passage re-ranking for passage pruning. Through our experiments, MGFiD outperforms existing models on the Natural Questions (NQ) and TriviaQA (TQA) datasets, highlighting the benefits of its multi-granularity solution.

Model Architecture