mlsanityData to 7 Oct 2026

BERT with History Answer Embedding for Conversational Question Answering

arXiv 1905.05412 ↗First posted 14 May 2019cs.IRcited by 67

Not on the map. Why?

Abstract (arXiv)

Conversational search is an emerging topic in the information retrieval community. One of the major challenges to multi-turn conversational search is to model the conversation history to answer the current question. Existing methods either prepend history turns to the current question or use complicated attention mechanisms to model the history. We propose a conceptually simple yet highly effective approach referred to as history answer embedding. It enables seamless integration of conversation history into a conversational question answering (ConvQA) model built on BERT (Bidirectional Encoder Representations from Transformers). We first explain our view that ConvQA is a simplified but concrete setting of conversational search, and then we provide a general framework to solve ConvQA. We further demonstrate the effectiveness of our approach under this framework. Finally, we analyze the impact of different numbers of history turns under different settings to provide new insights into conversation history modeling in ConvQA.

Key facts. Cited by 67 papers in the map (data through 7 Oct 2026). First posted on arXiv 14 May 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 22; 2022: 16; 2023: 14; 2024: 7; 2025: 7; 2026: 1.

67 papers.

Sort:

By area:

  1. 2021Sequence Parallelism: Long Sequence Training from System Perspectivecited by 125
  2. 2021TopiOCQA: Open-domain Conversational Question Answering with Topic Switchingcited by 95
  3. 2023Let the LLMs Talk: Simulating Human-to-Human Conversational QA via Zero-Shot LLM-to-LLM Interactionscited by 70
  4. 2021Go Wider Instead of Deepercited by 56
  5. 2021Natural Language Understanding with Privacy-Preserving BERTcited by 54
  6. 2022PACIFIC: Towards Proactive Conversational Question Answering over Tabular and Textual Data in Financecited by 45
  7. 2023MatSci-NLP: Evaluating Scientific Language Models on Materials Science Language Tasks Using Text-to-Schema Modelingcited by 35
  8. 2021Conversational Question Answering: A Surveycited by 31
  9. 2021Learn to Resolve Conversational Dependency: A Consistency Training Framework for Conversational Question Answeringcited by 27
  10. 2021An Efficient DP-SGD Mechanism for Large Scale NLP Modelscited by 27
  11. 2022Conversational Question Answering on Heterogeneous Sourcescited by 26
  12. 2022Chart Question Answering: State of the Art and Future Directionscited by 26
38 more
  1. 2021A Short Survey of Pre-trained Language Models for Conversational AI-A NewAge in NLPcited by 25
  2. 2023Personalized Large Language Model Assistant with Evolving Conditional Memorycited by 24
  3. 2025iAgent: LLM Agent as a Shield between User and Recommender Systemscited by 23
  4. 2021Structural Pre-training for Dialogue Comprehensioncited by 20
  5. 2021Ditch the Gold Standard: Re-evaluating Conversational Question Answeringcited by 19
  6. 2021Reinforcement Learning from Reformulations in Conversational Question Answering over Knowledge Graphscited by 18
  7. 2022Saving Dense Retriever from Shortcut Dependency in Conversational Searchcited by 18
  8. 2021Question Answering Survey: Directions, Challenges, Datasets, Evaluation Matricescited by 17
  9. 2022Generating Information-Seeking Conversations from Unlabeled Documentscited by 17
  10. 2021RoR: Read-over-Read for Long Document Machine Reading Comprehensioncited by 15
  11. 2021BERT-CoQAC: BERT-based Conversational Question Answering in Contextcited by 13
  12. 2021Enhanced Speaker-aware Multi-party Multi-turn Dialogue Comprehensioncited by 13
  13. 2023Implementing BERT and fine-tuned RobertA to detect AI generated news by ChatGPTcited by 13
  14. 2021Advances in Multi-turn Dialogue Comprehension: A Surveycited by 12
  15. 2022On the Robustness of Dialogue History Representation in Conversational Question Answering: A Comprehensive Study and a New Prompt-based Methodcited by 12
  16. 2021Speech Recognition by Simply Fine-tuning BERTcited by 11
  17. 2021DialogueBERT: A Self-Supervised Learning based Dialogue Pre-training Encodercited by 11
  18. 2023Legal Question-Answering in the Indian Context: Efficacy, Challenges, and Potential of Modern AI Modelscited by 10
  19. 2021Sentence Extraction-Based Machine Reading Comprehension for Vietnamesecited by 9
  20. 2022Neural Rankers for Effective Screening Prioritisation in Medical Systematic Review Literature Searchcited by 9
  21. 2022Open-Domain Conversational Question Answering with Historical Answerscited by 8
  22. 2024SubjECTive-QA: Measuring Subjectivity in Earnings Call Transcripts' QA Through Six-Dimensional Feature Analysiscited by 8
  23. 2022Interactive Question Answering Systems: Literature Reviewcited by 7
  24. 2023Robust Training for Conversational Question Answering Models with Reinforced Reformulation Generationcited by 7
  25. 2021SILT: Efficient transformer training for inter-lingual inferencecited by 5
  26. 2022From Rewriting to Remembering: Common Ground for Conversational QA Modelscited by 5
  27. 2023PCoQA: Persian Conversational Question Answering Datasetcited by 5
  28. 2021Weakly-Supervised Open-Retrieval Conversational Question Answeringcited by 4
  29. 2022A Study on Transformer Configuration and Training Objectivecited by 4
  30. 2023Learning to Select the Relevant History Turns in Conversational Question Answeringcited by 4
  31. 2023Keeping the Questions Conversational: Using Structured Representations to Resolve Dependency in Conversational Question Answeringcited by 3
  32. 2024UniRetriever: Multi-task Candidates Selection for Various Context-Adaptive Conversational Retrievalcited by 3
  33. 2025Multi-Agent Actor-Critic Generative AI for Query Resolution and Analysiscited by 3
  34. 2025Towards Adaptive Context Management for Intelligent Conversational Question Answeringcited by 3
  35. 2023Realistic Conversational Question Answering with Answer Selection based on Calibrated Confidence and Uncertainty Measurementcited by 2
  36. 2024Consistency Training by Synthetic Question Generation for Conversational Question Answeringcited by 2
  37. 2024Enhancing ID-based Recommendation with Large Language Modelscited by 2
  38. 2022Multifaceted Improvements for Conversational Open-Domain Question Answeringcited by 1

50 most cited of 67 All 67 (JSON)