MC-indexing: Effective Long Document Retrieval via Multi-view Content-aware Indexing
Kuicai Dong, Derrick Goh Xin Deik, Yi Quan Lee, Hao Zhang, Xiang‐Yang Li, Cong Zhang, Yong Liu · 2024
Long document question answering (DocQA) aims to answer questions from long documents over 10k words.They usually contain content structures such as sections, sub-sections, and paragraph demarcations.However, the indexing methods of long documents remain underexplored, while existing systems generally employ fixed-length chunking.As they do not consider content structures, the resultant chunks can exclude vital information or include irrelevant content.Motivated by this, we propose the Multi-view Content-aware indexing (MCindexing) for more effective long DocQA via (i) segment structured document into content chunks, and (ii) represent each content chunk in raw-text, keywords, and summary views.We highlight that MC-indexing requires neither training nor fine-tuning.Having plug-and-play capability, it can be seamlessly integrated with any retrievers to boost their performance.Besides, we propose a long DocQA dataset that includes not only question-answer pairs, but also their document structure and answer scope.Compared to state-of-art chunking schemes, MC-indexing has significantly increased the recall by 42.8%, 30.0%, 23.9%, and 16.3% via top k = 1.5, 3, 5, and 10 respectively.These improved scores are the average of 8 widely used retrievers (2 sparse and 6 dense) via extensive experiments.