English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

Open-Retrieval Conversational Question Answering (ORConvQA), SIGIR 2020

Forum topic · 小凯 · 2026-07-05

Summary

This forum post indexes the SIGIR 2020 paper "Open-Retrieval Conversational Question Answering" (ORConvQA), published in the ACM Digital Library at https://dl.acm.org/doi/abs/10.1145/3397271.3401110. The paper addresses open-retrieval conversational question answering, where a system must answer multi-turn questions by retrieving evidence from a large open corpus rather than from a fixed set of pre-selected passages. The post situates the work within conversational search and search engine evaluation, outlining the typical pipeline of dense/sparse query representation, retrievers, rerankers, and generators, along with learning strategies such as supervised fine-tuning, contrastive learning, and reinforcement learning. It also discusses evaluation practice (MS MARCO, Natural Questions, BEIR; nDCG@10, MRR, Recall@k), limitations such as benchmark-user distribution mismatch and cross-lingual generalization, and open problems including evaluation trustworthiness, latency and cost, hallucination, safety, and multimodal extension. Cross-references to related surveys and systems on conversational and agentic search are provided for readers building a reading list along the retrieval, ranking, generation, and evaluation pipeline.

Open-Retrieval Conversational Question Answering, SIGIR 2020

Overview

This entry indexes the SIGIR 2020 paper "Open-Retrieval Conversational Question Answering" (commonly known as ORConvQA).

| Field | Content | |---|---| | Title | Open-Retrieval Conversational Question Answering, SIGIR 2020 | | Source | https://dl.acm.org/doi/abs/10.1145/3397271.3401110 | | Type | Academic paper | | Sections | Conversational Search; Evaluation of Search Engines |

Background and Motivation

The paper targets open-retrieval conversational question answering, where a system answers multi-turn questions by retrieving evidence from a large open corpus rather than a fixed, pre-filtered passage set. Traditional pipelines that separate retrieval, ranking, and generation struggle with user intent understanding across turns, multi-hop reasoning, and incorporation of real-time knowledge — challenges this work addresses at the intersection of conversational search and open-domain information access.

Core Contributions (per the entry's framing)

  • A unified perspective on the problem domain, placing scattered related work into a comparable framework.
  • A clear decomposition of method components: representation learning, retrievers, rerankers, planners, generators, and feedback mechanisms.
  • Reproducible benchmarks, datasets, and taxonomies that lower the entry cost for follow-up research.
  • Discussion of interfaces with emerging paradigms such as LLM tool calling, reinforcement learning, and multi-agent collaboration.
  • Open problems: evaluation trustworthiness, latency and cost, hallucination and safety, cross-lingual and multimodal extension.
  • Typical Method Pipeline

    1. Input and representation — encode queries, documents, and conversational context into dense or sparse representations. 2. Core modules — retriever, reranker, planner, memory, and tool interfaces, composed in series or parallel. 3. Learning strategies — supervised fine-tuning, contrastive learning, distillation, reinforcement learning, synthetic data bootstrapping. 4. Inference — single-pass or iterative retrieval, parallel sub-queries, early stopping and budget control.

    Evaluation

    Common setup in this line of work:

  • Datasets: MS MARCO, BEIR, Natural Questions, domain corpora.
  • Metrics: nDCG@10, MRR, Recall@k, Hit@k, task success rate, latency and token cost.
  • Baselines: BM25, dense retrieval, cross-encoder reranking, retrieval-free LLMs, commercial search APIs.
  • Ablations: contribution of retrieval steps, reranking depth, and training data scale.
  • Exact quantitative results should be verified against the original PDF.

    Takeaways

    1. Architecture: cascaded retrieval + reranking + generation remains mainstream; agentic paradigms increasingly treat retrieval policy itself as learnable. 2. Data: high-quality instruction data and click/session logs matter; synthetic data requires leakage and distribution-shift safeguards. 3. Evaluation: the gap between offline metrics and online satisfaction is widening; LLM-as-judge needs cross-validation with human assessment. 4. Productization: latency, cost, explainability, and safety are hard constraints for deployment.

    Related Entries

  • A Survey of Conversational Search, Sep 2025, ACM
  • Engineering Conversational Search Systems: A Review of Applications
  • Agentic Conversational Search with Contextualized Reasoning via Reinforcement Learning
  • CTR-Guided Generative Query Suggestion in Conversational Search, EMNLP
  • ChatRetriever: Adapting Large Language Models for Generalized and Robust Retrieval
  • CoSearchAgent: A Lightweight Collaborative Search Agent with Large Language Models
  • Reference

  • Original paper: Open-Retrieval Conversational Question Answering, SIGIR 2020. DOI: 10.1145/3397271.3401110

Tags

#conversational-search#question-answering#information-retrieval#open-retrieval#rag#sigir-2020#search-evaluation

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/178208516