mlsanityData to 7 Oct 2026

How Additional Knowledge can Improve Natural Language Commonsense Question Answering?

arXiv 1909.08855 ↗First posted 19 Sep 2019cs.CL cs.IR cs.LGcited by 22

Not on the map. Why?

Abstract (arXiv)

Recently several datasets have been proposed to encourage research in Question Answering domains where commonsense knowledge is expected to play an important role. Recent language models such as ROBERTA, BERT and GPT that have been pre-trained on Wikipedia articles and books have shown reasonable performance with little fine-tuning on several such Multiple Choice Question-Answering (MCQ) datasets. Our goal in this work is to develop methods to incorporate additional (commonsense) knowledge into language model-based approaches for better question-answering in such domains. In this work, we first categorize external knowledge sources, and show performance does improve on using such sources. We then explore three different strategies for knowledge incorporation and four different models for question-answering using external commonsense knowledge. We analyze our predictions to explore the scope of further improvements.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). First posted on arXiv 19 Sep 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 8; 2022: 6; 2023: 4; 2024: 3; 2025: 0; 2026: 1.

22 papers.

Sort:

By area:

  1. 2021Generated Knowledge Prompting for Commonsense Reasoningcited by 213
  2. 2021The Web Is Your Oyster - Knowledge-Intensive NLP against a Very Large Web Corpuscited by 60
  3. 2023NormBank: A Knowledge Bank of Situational Social Normscited by 60
  4. 2022Rainier: Reinforced Knowledge Introspector for Commonsense Question Answeringcited by 43
  5. 2021Human Parity on CommonsenseQA: Augmenting Self-Attention with External Attentioncited by 40
  6. 2022Kformer: Knowledge Injection in Transformer Feed-Forward Layerscited by 37
  7. 2023Large Language Models are Clinical Reasoners: Reasoning-Aware Diagnosis Framework with Prompt-Generated Rationalescited by 33
  8. 2023Logical Reasoning over Natural Language as Knowledge Representation: A Surveycited by 32
  9. 2022A Survey of Knowledge-Intensive NLP with Pre-Trained Language Modelscited by 30
  10. 2021Incorporating Commonsense Knowledge Graph in Pretrained Models for Social Commonsense Taskscited by 24
  11. 2021Self-Supervised Test-Time Learning for Reading Comprehensioncited by 22
  12. 2023Self-Consistent Narrative Prompts on Abductive Natural Language Inferencecited by 11
10 more
  1. 2022Embarrassingly Simple Performance Prediction for Abductive Natural Language Inferencecited by 5
  2. 2021Inside ASCENT: Exploring a Deep Commonsense Knowledge Base and its Usage in Question Answeringcited by 3
  3. 2022A Survey on Knowledge-Enhanced Pre-trained Language Modelscited by 3
  4. 2021Semantic Categorization of Social Knowledge for Commonsense Question Answeringcited by 1
  5. 2022A Theoretically Grounded Benchmark for Evaluating Machine Commonsensecited by 1
  6. 2024Synergizing Machine Learning & Symbolic Methods: A Survey on Hybrid Approaches to Natural Language Processingcited by 1
  7. 2024Rule or Story, Which is a Better Commonsense Expression for Talking with Large Language Models?cited by 1
  8. 2024Zero-shot Commonsense Reasoning over Machine Imaginationcited by 1
  9. 2021Go Beyond Plain Fine-tuning: Improving Pretrained Models for Social Commonsensecited by 0
  10. 2026Enhancing Zero-shot Commonsense Reasoning by Integrating Visual Knowledge via Machine Imaginationcited by 0