Combing Context and Commonsense Knowledge Through Neural Networks for Solving Winograd Schema Problems
By QUAN LIU, Hui Jiang, Zhenhua Ling, Xiao-Dan Zhu, Si Wei, Yu Hu. 2016
35 citations recorded by the source corpus.
Subfields: Natural Language Processing, Prompting & Reasoning
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Natural Language Processing
- Jianfeng Gao
- Xiaodong Liu
- Weizhu Chen
- Pengcheng He
- Richard Socher
- Caiming Xiong
- Yejin Choi
- Mohit Bansal
In Prompting & Reasoning
- Weizhu Chen
- Jianfeng Gao
- Ali Emami
- Xiaodong Liu
- Quoc V. Le
- Kaheer Suleman
- Shuohang Wang
- Jackie Chi Kit Cheung
Citations in the corpus
- A Simple Method for Commonsense Reasoning (2018, methodology): “[27], who makes use of three knowledge bases and a supervised deep neural network.”
- A Hybrid Neural Network Model for Commonsense Reasoning (2019, methodology): “While traditional methods of commonsense reasoning rely heavily on human-crafted features and knowledge bases (Rahman and Ng, 2012a; Sharma et al., 2015; Schüller, 2014; Bailey et al., 2015; Liu et al., 2017), we explore in this study machine learning approaches using deep neural networks (DNN).”
- A Knowledge Hunting Framework for Common Sense Reasoning (2018, methodology): “We compare these to the systems of Sharma et al. (2015) (S2015) and Liu et al. (2017) (L2017).”
- WinoWhy: A Deep Diagnosis of Essential Commonsense Knowledge for Answering Winograd Schema Challenge (2020, background): “Conventionally, people tried to leverage crowdsourced commonsense knowledge bases (Liu et al., 2017) or search engines (Emami et al.”
- Unsupervised Deep Structured Semantic Models for Commonsense Reasoning (2019, methodology): “Neural Knowledge Activated Method (NKAM) (Liu et al., 2017) trained a binary classification model based on whether the word pairs appear in the knowledge base.”
- A Generalized Knowledge Hunting Framework for the Winograd Schema Challenge (2018, background): “There have been efforts to encode such knowledge directly, using logical formalisms (Bailey et al., 2015) or by using deep learning models (Liu et al., 2016a); however, these approaches have so far solved only restricted subsets of WSC questions with high precision, and show limited ability to…”