mlsanityData to 14 Oct 2026

Answer Generation for Retrieval-based Question Answering Systems

arXiv 2106.00955 ↗First posted 2 Jun 2021cs.CLcited by 13

Not on the map. Why?

Abstract (arXiv)

Recent advancements in transformer-based models have greatly improved the ability of Question Answering (QA) systems to provide correct answers; in particular, answer sentence selection (AS2) models, core components of retrieval-based systems, have achieved impressive results. While generally effective, these models fail to provide a satisfying answer when all retrieved candidates are of poor quality, even if they contain correct information. In AS2, models are trained to select the best answer sentence among a set of candidates retrieved for a given question. In this work, we propose to generate answers from a set of AS2 top candidates. Rather than selecting the best candidate, we train a sequence to sequence transformer model to generate an answer from a candidate set. Our tests on three English AS2 datasets show improvement up to 32 absolute points in accuracy over the state of the art.

Key facts. Cited by 13 papers in the map (data through 14 Oct 2026). Builds on 17 of its 33 references that are in the map. First posted on arXiv 2 Jun 2021.

Builds on

17 of 33 references.

References · 17

  1. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  2. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  4. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,893
  5. 2016MS MARCO: A Human Generated MAchine Reading COmprehension Datasetcited by 1,605
  6. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,210
  7. 2020How Much Knowledge Can You Pack Into the Parameters of a Language Model?cited by 719
  8. 2020UnifiedQA: Crossing Format Boundaries With a Single QA Systemcited by 476
  9. 2020Autoregressive Entity Retrievalcited by 334
  10. 2021The Expando-Mono-Duo Design Pattern for Text Ranking with Pretrained Sequence-to-Sequence Modelscited by 81
  11. 2019TANDA: Transfer and Adapt Pre-Trained Transformer Models for Answer Sentence Selectioncited by 74
  12. 2020Low-Resource Domain Adaptation for Compositional Task-Oriented Semantic Parsingcited by 72
5 more
  1. 2018The price of debiasing automatic metrics in natural language evaluationcited by 60
  2. 2020Don't Parse, Generate! A Sequence to Sequence Architecture for Task-Oriented Semantic Parsingcited by 59
  3. 2019Joint Learning of Answer Selection and Answer Summary Generation in Community Question Answeringcited by 25
  4. 2020The Cascade Transformer: an Application for Efficient Answer Sentence Selectioncited by 20
  5. 2021Modeling Context in Answer Sentence Selection Systems on a Latency Budgetcited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 1; 2022: 1; 2023: 6; 2024: 3; 2025: 1; 2026: 1.

13 papers.

Sort:

By area:

  1. 2021Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Surveycited by 463
  2. 2024DocFinQA: A Long-Context Financial Reasoning Datasetcited by 60
  3. 2023Knowledge-Augmented Large Language Models for Personalized Contextual Query Suggestioncited by 43
  4. 2023Answer Mining from a Pool of Images: Towards Retrieval-Based Visual Question Answeringcited by 10
  5. 2022Knowledge Transfer from Answer Ranking to Answer Generationcited by 6
  6. 2023Learning Answer Generation using Supervision from Automatic Question Answering Evaluatorscited by 3
  7. 2024Measuring Retrieval Complexity in Question Answering Systemscited by 3
  8. 2023Cross-Lingual Knowledge Distillation for Answer Sentence Selection in Low-Resource Languagescited by 2
  9. 2024FastFiD: Improve Inference Efficiency of Open Domain Question Answering via Sentence Selectioncited by 2
  10. 2023SQUARE: Automatic Question Answering Evaluation using Multiple Positive and Negative Referencescited by 1
  11. 2025The illusion of a perfect metric: Why evaluating AI's words is harder than it lookscited by 1
  12. 2023Question-Context Alignment and Answer-Context Dependencies for Effective Answer Sentence Selectioncited by 0
1 more
  1. 2026BEST-KAG: Enhancing Question Answering of Building Engineering Standards with Multimodal Knowledge Graph Modeling and Large Language Modelcited by 0