{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/end-to-end-multihop-retrieval-for","title":"Iterative Hierarchical Attention for Answering Complex Questions over Long Documents","arxiv_id":"2106.00200","date":"2021-06-01","proceeding":null,"authors":["Haitian Sun","William W. Cohen","Ruslan Salakhutdinov"],"abstract":"We propose a new model, DocHopper, that iteratively attends to different parts of long, hierarchically structured documents to answer complex questions. Similar to multi-hop question-answering (QA) systems, at each step, DocHopper uses a query $q$ to attend to information from a document, combines this ``retrieved'' information with $q$ to produce the next query. However, in contrast to most previous multi-hop QA systems, DocHopper is able to ``retrieve'' either short passages or long sections of the document, thus emulating a multi-step process of ``navigating'' through a long document to answer a question. To enable this novel behavior, DocHopper does not combine document information with $q$ by concatenating text to the text of $q$, but by combining a compact neural representation of $q$ with a compact neural representation of a hierarchical part of the document, which can potentially be quite large. We experiment with DocHopper on four different QA tasks that require reading long and complex documents to answer multi-hop questions, and show that DocHopper achieves state-of-the-art results on three of the datasets. Additionally, DocHopper is efficient at inference time, being 3--10 times faster than the baselines.","url_abs":"https://arxiv.org/abs/2106.00200v2","url_pdf":"https://arxiv.org/pdf/2106.00200v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"multi-hop-question-answering","task_name":"Multi-hop Question Answering"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"sentence-embedding","task_name":"Sentence Embedding"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bart","method_name":"BART"},{"method_slug":"bert","method_name":"BERT"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-linear-decay","method_name":"Linear Warmup With Linear Decay"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"rag","method_name":"RAG"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"wordpiece","method_name":"WordPiece"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/question-answering-on-conditionalqa","task":"Question Answering","dataset":"ConditionalQA","model":"DocHopper","rank_in_archive_order":2,"of":3,"metrics":{"Conditional (answers)":"42.0 / 46.4","Conditional (w/ conditions)":"3.1 / 3.8","Overall (answers)":"40.6 / 45.2","Overall (w/ conditions)":"31.9 / 36.0"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-hybridqa","task":"Question Answering","dataset":"HybridQA","model":"DocHopper","rank_in_archive_order":3,"of":4,"metrics":{"ANS-EM":"46.3"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2106.00200","atlas_url":"https://app.syntology.ai/?focus=2106.00200","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}