mlsanityData to 13 Oct 2026

Question-Answer Sentence Graph for Joint Modeling Answer Selection

arXiv 2203.03549 ↗First posted 16 Feb 2022cs.CL cs.AIcited by 6

Not on the map. Why?

Abstract (arXiv)

This research studies graph-based approaches for Answer Sentence Selection (AS2), an essential component for retrieval-based Question Answering (QA) systems. During offline learning, our model constructs a small-scale relevant training graph per question in an unsupervised manner, and integrates with Graph Neural Networks. Graph nodes are question sentence to answer sentence pairs. We train and integrate state-of-the-art (SOTA) models for computing scores between question-question, question-answer, and answer-answer pairs, and use thresholding on relevance scores for creating graph edges. Online inference is then performed to solve the AS2 task on unseen queries. Experiments on two well-known academic benchmarks and a real-world dataset show that our approach consistently outperforms SOTA QA baseline models.

Key facts. Cited by 6 papers in the map (data through 13 Oct 2026). Builds on 16 of its 41 references that are in the map. First posted on arXiv 16 Feb 2022.

Builds on

16 of 41 references.

References · 16

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,093
  2. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,797
  3. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,716
  4. 2017Reading Wikipedia to Answer Open-Domain Questionscited by 777
  5. 2019Hierarchical Graph Network for Multi-hop Question Answeringcited by 83
  6. 2019TANDA: Transfer and Adapt Pre-Trained Transformer Models for Answer Sentence Selectioncited by 74
  7. 2021KG-FiD: Infusing Knowledge Graph in Fusion-in-Decoder for Open-Domain Question Answeringcited by 67
  8. 2018Learning a Deep Listwise Context Model for Ranking Refinementcited by 62
  9. 2017Hyperbolic Representation Learning for Fast and Efficient Neural Question Answeringcited by 23
  10. 2019A Compare-Aggregate Model with Latent Clustering for Answer Selectioncited by 19
  11. 2016Sentence Similarity Learning by Lexical Decomposition and Compositioncited by 16
  12. 2021Joint Models for Answer Verification in Question Answering Systemscited by 13
4 more
  1. 2020Answer Ranking for Product-Related Questions via Multiple Semantic Relations Modelingcited by 10
  2. 2021Graph-Based Tri-Attention Network for Answer Ranking in CQAcited by 8
  3. 2021Contextualized Knowledge-aware Attentive Neural Network: Enhancing Answer Selection with Knowledgecited by 7
  4. 2021Multi-Relational Graph based Heterogeneous Multi-Task Learning in Community Question Answeringcited by 4

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2022: 1; 2023: 2; 2024: 1; 2025: 1; 2026: 1.

6 papers.

  1. 2024CABINET: Content Relevance based Noise Reduction for Table Question Answeringcited by 23
  2. 2023keqing: knowledge-based question answering is a nature chain-of-thought mentor of LLMcited by 16
  3. 2022Dual-Geometric Space Embedding Model for Two-View Knowledge Graphscited by 12
  4. 2023Machine Reading Comprehension using Case-based Reasoningcited by 2
  5. 2025Counting Still Counts: Understanding Neural Complex Query Answering Through Query Relaxationcited by 0
  6. 2026BengaliMCQ: Automatic Generation and Answer Prediction of Academic Multiple-Choice Questions in a Low-Resource Languagecited by 0