Yuanfudao at SemEval-2018 Task 11: Three-way Attention and Relational Knowledge for Commonsense Machine Comprehension
Not on the map. Why?
Abstract (arXiv)
This paper describes our system for SemEval-2018 Task 11: Machine Comprehension using Commonsense Knowledge. We use Three-way Attentive Networks (TriAN) to model interactions between the passage, question and answers. To incorporate commonsense knowledge, we augment the input with relation embedding from the graph of general knowledge ConceptNet (Speer et al., 2017). As a result, our system achieves state-of-the-art performance with 83.95% accuracy on the official test data. Code is publicly available at https://github.com/intfloat/commonsense-rc
Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). First posted on arXiv 1 Mar 2018.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 8; 2022: 4.
12 papers.
- 2021DISCOS: Bridging the Gap between Discourse Knowledge and Commonsense Knowledgecited by 26
- 2021Incorporating Commonsense Knowledge Graph in Pretrained Models for Social Commonsense Taskscited by 24
- 2021Self-Teaching Machines to Read and Comprehend with Large-Scale Multi-Subject Question-Answering Datacited by 6
- 2021Encoding Explanatory Knowledge for Zero-shot Science Question Answeringcited by 3
- 2022Medical Knowledge Graph QA for Drug-Drug Interaction Prediction based on Multi-hop Machine Reading Comprehensioncited by 1
- 2021Understanding in Artificial Intelligencecited by 0
- 2021Go Beyond Plain Fine-tuning: Improving Pretrained Models for Social Commonsensecited by 0
- 2021Coarse-to-Careful: Seeking Semantic-related Knowledge for Open-domain Commonsense Question Answeringcited by 0
- 2021Leveraging Commonsense Knowledge on Classifying False News and Determining Checkworthiness of Claimscited by 0
- 2022elBERto: Self-supervised Commonsense Learning for Question Answeringcited by 0
- 2022Why Do Neural Language Models Still Need Commonsense Knowledge to Handle Semantic Variations in Question Answering?cited by 0
- 2022Modular Approach to Machine Reading Comprehension: Mixture of Task-Aware Expertscited by 0
- 2022Medical Knowledge Graph QA for Drug-Drug Interaction Prediction based on Multi-hop Machine Reading Comprehension19 Dec 2022
- 2022Modular Approach to Machine Reading Comprehension: Mixture of Task-Aware Experts4 Oct 2022
- 2022Why Do Neural Language Models Still Need Commonsense Knowledge to Handle Semantic Variations in Question Answering?1 Sep 2022
- 2022elBERto: Self-supervised Commonsense Learning for Question Answering17 Mar 2022
- 2021Leveraging Commonsense Knowledge on Classifying False News and Determining Checkworthiness of Claims8 Aug 2021
- 2021Coarse-to-Careful: Seeking Semantic-related Knowledge for Open-domain Commonsense Question Answering4 Jul 2021
- 2021Go Beyond Plain Fine-tuning: Improving Pretrained Models for Social Commonsense12 May 2021
- 2021Encoding Explanatory Knowledge for Zero-shot Science Question Answering12 May 2021
- 2021Incorporating Commonsense Knowledge Graph in Pretrained Models for Social Commonsense Tasks12 May 2021
- 2021Self-Teaching Machines to Read and Comprehend with Large-Scale Multi-Subject Question-Answering Data1 Feb 2021
- 2021Understanding in Artificial Intelligence17 Jan 2021
- 2021DISCOS: Bridging the Gap between Discourse Knowledge and Commonsense Knowledge1 Jan 2021