Yicheng Wang
Yicheng Wang has 2 papers in our library, in 2018, most of them on Reasoning, Question answering; often with Mohit Bansal, Yixin Nie.
OpenAlex · ORCID · h-index 24 · 197 works · 2,373 citations OpenAlex, 2026-10-14
📄 2 works in our library · 🔗 Cited 111 times in our library · ⭐ Paper Stars ranking: #3990
Affiliations
🔬China Institute of Water Resources and Hydropower ResearchBeijing ·
China2008–2026 · 31 papers🎓National University of Defense TechnologyChangsha ·
China2018–2026 · 14 papers🎓University of AlbertaEdmonton ·
Canada2025–2026 · 5 papers🎓Beijing Institute of Fashion TechnologyBeijing ·
China2024–2026 · 3 papers🎓Beijing University of Posts and TelecommunicationsBeijing ·
China2025–2026 · 3 papers🎓Anhui Agricultural UniversityHefei ·
China2025–2026 · 2 papers🎓East China Normal UniversityShanghai ·
China2025–2026 · 2 papers🎓Hefei Normal UniversityHefei ·
China2026 · 1 paper🔬State Key Laboratory of Basin Water Cycle Simulation and RegulationBeijing2014–2025 · 16 papers🔬State Key Laboratory of Pulsed Power Laser TechnologyHefei2022–2025 · 12 papers
Concepts, shelves and topics
📚 Shelves 5The field of science this work belongs to (OpenAlex fields).Arts and Humanities · 2 worksComputer Science · 2 worksArtificial Intelligence · 2 worksLanguage and Linguistics · 2 worksComputer Vision and Pattern Recognition · 1 work
🧭 Topics 2Research subjects and languages the work is about.Reasoning · 2 worksQuestion answering · 1 work
Works by year
2010s
Papers
- Commonsense for Generative Multi-Hop Question Answering Tasks (2018 · 229 citations)
Most reading-comprehension QA research targets extractive, fact-lookup questions. This EMNLP 2018 paper addresses the harder generative setting of NarrativeQA. There, answers must be composed from several scattered parts of a long story, and they often depend on implicit links that people bridge with everyday… - Analyzing Compositionality-Sensitivity of NLI Models (2018 · 119 citations)
NLI systems reach near-human accuracy on SNLI and MNLI. This paper asks whether they use sentence structure or mostly match words. The authors test seven strong models, both sentence encoders and co-attention models. They build two rule-based adversaries that keep the vocabulary of the premise but change its meaning.…
Co-authors here
Venues
- Conference on Empirical Methods in Natural Language Processing (EMNLP): EMNLP 2018
- Proceedings of the AAAI Conference on Artificial Intelligence: Proceedings of the AAAI Conference on Artificial Intelligence 2018
Cited by
Updated
This page in Markdown → https://md.research.elamur.ai/free/en/authors/yicheng-wang/