mlsanityData to 7 Oct 2026

AmazonQA: A Review-Based Question Answering Task

arXiv 1908.04364 ↗First posted 12 Aug 2019cs.CL cs.IRcited by 43

Not on the map. Why?

Abstract (arXiv)

Every day, thousands of customers post questions on Amazon product pages. After some time, if they are fortunate, a knowledgeable customer might answer their question. Observing that many questions can be answered based upon the available product reviews, we propose the task of review-based QA. Given a corpus of reviews and a question, the QA system synthesizes an answer. To this end, we introduce a new dataset and propose a method that combines information retrieval techniques for selecting relevant reviews (given a question) and "reading comprehension" models for synthesizing an answer (given a question and review). Our dataset consists of 923k questions, 3.6M answers and 14M reviews across 156k products. Building on the well-known Amazon dataset, we collect additional annotations, marking each question as either answerable or unanswerable based on the available reviews. A deployed system could first classify a question as answerable and then attempt to generate an answer. Notably, unlike many popular QA datasets, here, the questions, passages, and answers are all extracted from real human interactions. We evaluate numerous models for answer generation and propose strong baselines, demonstrating the challenging nature of this new task.

Key facts. Cited by 43 papers in the map (data through 7 Oct 2026). First posted on arXiv 12 Aug 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 5; 2022: 9; 2023: 6; 2024: 9; 2025: 10; 2026: 4.

43 papers.

Sort:

By area:

  1. 2022One Embedder, Any Task: Instruction-Finetuned Text Embeddingscited by 329
  2. 2024Nomic Embed: Training a Reproducible Long Context Text Embeddercited by 255
  3. 2024Generative Representational Instruction Tuningcited by 227
  4. 2021GALAXY: A Generative Pre-trained Model for Task-Oriented Dialog with Semi-Supervised Learning and Explicit Policy Injectioncited by 102
  5. 2021QA Dataset Explosion: A Taxonomy of NLP Resources for Question Answering and Reading Comprehensioncited by 91
  6. 2023Context-faithful Prompting for Large Language Modelscited by 76
  7. 2024eCeLLM: Generalizing Large Language Models for E-commerce from Large-scale, High-quality Instruction Datacited by 44
  8. 2022SPACE-3: Unified Dialog Model Pre-training for Task-Oriented Dialog Understanding and Generationcited by 34
  9. 2022SPACE-2: Tree-Structured Semi-Supervised Contrastive Pre-training for Task-Oriented Dialog Understandingcited by 28
  10. 2021English Machine Reading Comprehension Datasets: A Surveycited by 26
  11. 2024Shopping MMLU: A Massive Multi-Task Online Shopping Benchmark for Large Language Modelscited by 20
  12. 2024Contextual Document Embeddingscited by 19
31 more
  1. 2021Towards Personalized Answer Generation in E-Commerce via Multi-Perspective Preference Modelingcited by 16
  2. 2025NeoBERT: A Next-Generation BERTcited by 14
  3. 2022Match-Prompt: Improving Multi-task Generalization Ability for Neural Text Matching via Prompt Learningcited by 10
  4. 2023Product Question Answering in E-Commerce: A Surveycited by 10
  5. 2026F2LLM-v2: Inclusive, Performant, and Efficient Embeddings for a Multilingual Worldcited by 10
  6. 2025WixQA: A Multi-Dataset Benchmark for Enterprise Retrieval-Augmented Generationcited by 9
  7. 2025F2LLM Technical Report: Matching SOTA Embedding Performance with 6 Million Open-Source Datacited by 8
  8. 2024Captions Speak Louder than Images: Generalizing Foundation Models for E-commerce from High-quality Multimodal Instruction Datacited by 6
  9. 2023QUADRo: Dataset and Models for QUestion-Answer Database Retrievalcited by 5
  10. 2024Database-Augmented Query Representation for Information Retrievalcited by 5
  11. 2025EcomMMMU: Strategic Utilization of Visuals for Robust Multimodal E-commerce Modelscited by 5
  12. 2025AIP: Subverting Retrieval-Augmented Generation via Adversarial Instructional Promptcited by 5
  13. 2024BSharedRAG: Backbone Shared Retrieval-Augmented Generation for the E-commerce Domaincited by 4
  14. 2025LEAF: Knowledge Distillation of Text Embedding Models with Teacher-Aligned Representationscited by 4
  15. 2021Distantly Supervised Transformers For E-Commerce Product QAcited by 3
  16. 2022PLAtE: A Large-scale Dataset for List Page Web Extractioncited by 3
  17. 2023UniPCM: Universal Pre-trained Conversation Model with Task-aware Automatic Promptcited by 3
  18. 2025Generative Representational Learning of Foundation Models for Recommendationcited by 2
  19. 2025Contextually Aware E-Commerce Product Question Answering using RAGcited by 2
  20. 2026SAGE: A Self-Evolving Agentic Graph-Memory Engine for Structure-Aware Associative Memorycited by 2
  21. 2022Comparative Snippet Generationcited by 0
  22. 2022Mining Duplicate Questions of Stack Overflowcited by 0
  23. 2022Modular Approach to Machine Reading Comprehension: Mixture of Task-Aware Expertscited by 0
  24. 2022Answer ranking in Community Question Answering: a deep learning approachcited by 0
  25. 2023OpinionConv: Conversational Product Search with Grounded Opinionscited by 0
  26. 2023Answering Subjective Induction Questions on Products by Summarizing Multi-sources Multi-viewpoints Knowledgecited by 0
  27. 2024Unlocking Markets: A Multilingual Benchmark to Cross-Market Question Answeringcited by 0
  28. 2025QQSUM: A Novel Task and Model of Quantitative Query-Focused Summarization for Review-based Product Question Answeringcited by 0
  29. 2025Improving Document Retrieval Coherence for Semantically Equivalent Queriescited by 0
  30. 2026Adapting Vision-Language Models for E-commerce Understanding at Scalecited by 0
  31. 2026ML-Embed: Inclusive and Efficient Embeddings for a Multilingual Worldcited by 0