# Knowledgeable Reader: Enhancing Cloze-Style Reading Comprehension with External Commonsense Knowledge

arXiv: https://arxiv.org/abs/1805.07858 · HTML: https://mlsanity.com/paper/1805.07858/

## Key facts

- Cited by 48 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 May 2018.

## Built on by (most cited first, 30 of 48)

- [QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering](https://mlsanity.com/paper/2104.06378/) (2021)
- [Making Large Language Models Better Reasoners with Step-Aware Verifier](https://mlsanity.com/paper/2206.02336/) (2022)
- [GreaseLM: Graph REASoning Enhanced Language Models for Question Answering](https://mlsanity.com/paper/2201.08860/) (2022)
- [Deep Bidirectional Language-Knowledge Graph Pretraining](https://mlsanity.com/paper/2210.09338/) (2022)
- [Active Prompting with Chain-of-Thought for Large Language Models](https://mlsanity.com/paper/2302.12246/) (2023)
- [Cumulative Reasoning with Large Language Models](https://mlsanity.com/paper/2308.04371/) (2023)
- [MISC: A MIxed Strategy-Aware Model Integrating COMET for Emotional Support Conversation](https://mlsanity.com/paper/2203.13560/) (2022)
- [Towards Interpreting and Mitigating Shortcut Learning Behavior of NLU Models](https://mlsanity.com/paper/2103.06922/) (2021)
- [Graph Neural Prompting with Large Language Models](https://mlsanity.com/paper/2309.15427/) (2023)
- [TIMEDIAL: Temporal Commonsense Reasoning in Dialog](https://mlsanity.com/paper/2106.04571/) (2021)
- [Automatic Story Generation: Challenges and Attempts](https://mlsanity.com/paper/2102.12634/) (2021)
- [Benchmarking Knowledge-Enhanced Commonsense Question Answering via Knowledge-to-Text Transformation](https://mlsanity.com/paper/2101.00760/) (2021)
- [Joint Biomedical Entity and Relation Extraction with Knowledge-Enhanced Collective Inference](https://mlsanity.com/paper/2105.13456/) (2021)
- [Reasoning Over Virtual Knowledge Bases With Open Predicate Relations](https://mlsanity.com/paper/2102.07043/) (2021)
- [Dynamic Semantic Graph Construction and Reasoning for Explainable Multi-hop Science Question Answering](https://mlsanity.com/paper/2105.11776/) (2021)
- [Meta Prompting for AI Systems](https://mlsanity.com/paper/2311.11482/) (2023)
- [BIC: Twitter Bot Detection with Text-Graph Interaction and Semantic Consistency](https://mlsanity.com/paper/2208.08320/) (2022)
- [Question-guided Knowledge Graph Re-scoring and Injection for Knowledge Graph Question Answering](https://mlsanity.com/paper/2410.01401/) (2024)
- [Guiding Neural Story Generation with Reader Models](https://mlsanity.com/paper/2112.08596/) (2021)
- [ComFact: A Benchmark for Linking Contextual Commonsense Knowledge](https://mlsanity.com/paper/2210.12678/) (2022)
- [Multi-turn Dialogue Reading Comprehension with Pivot Turns and Knowledge](https://mlsanity.com/paper/2102.05474/) (2021)
- [Elaboration-Generating Commonsense Question Answering at Scale](https://mlsanity.com/paper/2209.01232/) (2022)
- [FiTs: Fine-grained Two-stage Training for Knowledge-aware Question Answering](https://mlsanity.com/paper/2302.11799/) (2023)
- [Relation-Aware Language-Graph Transformer for Question Answering](https://mlsanity.com/paper/2212.00975/) (2022)
- [First Train to Generate, then Generate to Train: UnitedSynT5 for Few-Shot NLI](https://mlsanity.com/paper/2412.09263/) (2024)
- [Natural Language Processing with Commonsense Knowledge: A Survey](https://mlsanity.com/paper/2108.04674/) (2021)
- [IBERT: Idiom Cloze-style reading comprehension with Attention](https://mlsanity.com/paper/2112.02994/) (2021)
- [KGQuiz: Evaluating the Generalization of Encoded Knowledge in Large Language Models](https://mlsanity.com/paper/2310.09725/) (2023)
- [ArT: All-round Thinker for Unsupervised Commonsense Question-Answering](https://mlsanity.com/paper/2112.13428/) (2021)
- [Generalizable Neuro-symbolic Systems for Commonsense Question Answering](https://mlsanity.com/paper/2201.06230/) (2022)

## Abstract (arXiv)

We introduce a neural reading comprehension model that integrates external commonsense knowledge, encoded as a key-value memory, in a cloze-style setting. Instead of relying only on document-to-question interaction or discrete features as in prior work, our model attends to relevant external knowledge and combines this knowledge with the context representation before inferring the answer. This allows the model to attract and imply knowledge from an external knowledge source that is not explicitly stated in the text, but that is relevant for inferring the answer. Our model improves results over a very strong baseline on a hard Common Nouns dataset, making it a strong competitor of much more complex models. By including knowledge explicitly, our model can also provide evidence about the background knowledge used in the RC process.