{"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/normy-non-uniform-history-modeling-for-open","title":"NORMY: Non-Uniform History Modeling for Open Retrieval Conversational Question Answering","arxiv_id":"2402.04548","date":"2024-02-07","proceeding":null,"authors":["Muhammad Shihab Rashid","Jannat Ara Meem","Vagelis Hristidis"],"abstract":"Open Retrieval Conversational Question Answering (OrConvQA) answers a question given a conversation as context and a document collection. A typical OrConvQA pipeline consists of three modules: a Retriever to retrieve relevant documents from the collection, a Reranker to rerank them given the question and the context, and a Reader to extract an answer span. The conversational turns can provide valuable context to answer the final query. State-of-the-art OrConvQA systems use the same history modeling for all three modules of the pipeline. We hypothesize this as suboptimal. Specifically, we argue that a broader context is needed in the first modules of the pipeline to not miss relevant documents, while a narrower context is needed in the last modules to identify the exact answer span. We propose NORMY, the first unsupervised non-uniform history modeling pipeline which generates the best conversational history for each module. We further propose a novel Retriever for NORMY, which employs keyphrase extraction on the conversation history, and leverages passages retrieved in previous turns as additional context. We also created a new dataset for OrConvQA, by expanding the doc2dial dataset. We implemented various state-of-the-art history modeling techniques and comprehensively evaluated them separately for each module of the pipeline on three datasets: OR-QUAC, our doc2dial extension, and ConvMix. Our extensive experiments show that NORMY outperforms the state-of-the-art in the individual modules and in the end-to-end system.","url_abs":"https://arxiv.org/abs/2402.04548v1","url_pdf":"https://arxiv.org/pdf/2402.04548v1.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":[{"paper_slug":"normy-non-uniform-history-modeling-for-open","repo_url":"https://github.com/shihabrashid-ucr/normy","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"conversational-question-answering","task_name":"Conversational Question Answering"},{"task_slug":"keyphrase-extraction","task_name":"Keyphrase Extraction"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2402.04548","atlas_url":"https://app.syntology.ai/?focus=2402.04548","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}