ReCoRD: Bridging the Gap between Human and Machine Commonsense Reading Comprehension

Sheng Zhang, Xiaodong Liu, Jingjing Liu, Jianfeng Gao, Kevin Duh, Benjamin Van Durme

2018-10-30Reading ComprehensionCommon Sense ReasoningMachine Reading Comprehension
PaperPDF

Abstract

We present a large-scale dataset, ReCoRD, for machine reading comprehension requiring commonsense reasoning. Experiments on this dataset demonstrate that the performance of state-of-the-art MRC systems fall far behind human performance. ReCoRD represents a challenge for future research to bridge the gap between human and machine commonsense reading comprehension. ReCoRD is available at http://nlp.jhu.edu/record.

Results

TaskDatasetMetricValueModel
Common Sense ReasoningReCoRDEM45.4DocQA + ELMo
Common Sense ReasoningReCoRDF146.7DocQA + ELMo

Related Papers

Comparing Apples to Oranges: A Dataset & Analysis of LLM Humour Understanding from Traditional Puns to Topical Jokes2025-07-17LoSiA: Efficient High-Rank Fine-Tuning via Subnet Localization and Optimization2025-07-06DeRIS: Decoupling Perception and Cognition for Enhanced Referring Image Segmentation through Loopback Synergy2025-07-02Chaining Event Spans for Temporal Relation Grounding2025-06-17S2ST-Omni: An Efficient and Scalable Multilingual Speech-to-Speech Translation Framework via Seamless Speech-Text Alignment and Streaming Speech Generation2025-06-11EditInspector: A Benchmark for Evaluation of Text-Guided Image Edits2025-06-11CheckManual: A New Challenge and Benchmark for Manual-based Appliance Manipulation2025-06-11CoMuMDR: Code-mixed Multi-modal Multi-domain corpus for Discourse paRsing in conversations2025-06-10