Understanding the Behaviors of BERT in Ranking
원문 초록
This paper studies the performances and behaviors of BERT in ranking tasks. We explore several different ways to leverage the pre-trained BERT and fine-tune it on two ranking tasks: MS MARCO passage reranking and TREC Web Track ad hoc document ranking. Experimental results on MS MARCO demonstrate the strong effectiveness of BERT in question-answering focused passage ranking tasks, as well as the fact that BERT is a strong interaction-based seq2seq matching model. Experimental results on TREC show the gaps between the BERT pre-trained on surrounding contexts and the needs of ad hoc document ranking. Analyses illustrate how BERT allocates its attentions between query-document tokens in its Transformer layers, how it prefers semantic matches between paraphrase tokens, and how that differs with the soft match patterns learned by a click-trained neural ranker.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Knowledge-Aware Diverse Reranking for Cross-Source Question Answering
MM-R5: MultiModal Reasoning-Enhanced ReRanker via Reinforcement Learning for Document Retrieval
From Roots to Rewards: Dynamic Tree Reasoning with RL
Describe Anything Model for Visual Question Answering on Text-rich Images
Warehouse Spatial Question Answering with LLM Agent
Efficiency-Effectiveness Reranking FLOPs for LLM-based Rerankers
토론
이 논문과 연결된 포럼 글이 아직 없습니다.