paper-with-me

Papers

MICO: A Multi-alternative Contrastive Learning Framework for Commonsense Knowledge Representation

2022-10-14 · Ying Su, ZiHao Wang, Tianqing Fang, Hongming Zhang, Yangqiu Song, Tong Zhang

Commonsense reasoning tasks such as commonsense knowledge graph completion and commonsense question answering require powerful representation learning. In this paper, we propose to learn commonsense knowledge representation by MICO, a Multi-alternative contrastve learning framework on COmmonsense knowledge graphs (MICO). MICO generates the commonsense knowledge representation by contextual interaction between entity nodes and relations with multi-alternative contrastive learning. In MICO, the head and tail entities in an $(h,r,t)$ knowledge triple are converted to two relation-aware sequence pairs (a premise and an alternative) in the form of natural language. Semantic representations generated by MICO can benefit the following two tasks by simply comparing the distance score between the representations: 1) zero-shot commonsense question answering task; 2) inductive commonsense knowledge graph completion task. Extensive experiments show the effectiveness of our method.

📄 PDF Abstract BibTeX arXiv:2210.07570

Code (1)

hkust-knowcomp/mico 공식 구현 pytorch

Tasks

Contrastive LearningKnowledge Graph CompletionKnowledge GraphsQuestion AnsweringRepresentation LearningTask 2

Similar Papers 제목 키워드 기반

Prompting Contrastive Explanations for Commonsense Reasoning Tasks

2021-06-12 · Findings (ACL) 2021 8 · Bhargavi Paranjape, Julian Michael, Marjan Ghazvininejad, Luke Zettlemoyer 외

Many commonsense reasoning NLP tasks involve choosing between one or more possible answers to a question or prompt based on knowledge that is often implicit. Large pretrained language models (PLMs) can achieve near-human…

Attribute

Metadata-Induced Contrastive Learning for Zero-Shot Multi-Label Text Classification

2022-02-11 · Yu Zhang, Zhihong Shen, Chieh-Han Wu, Boya Xie 외

Large-scale multi-label text classification (LMTC) aims to associate a document with its relevant labels from a large candidate set. Most existing LMTC approaches rely on massive human-annotated training data, which are …

Contrastive LearningMulti Label Text ClassificationMulti-Label Text Classificationtext-classification+2

Str-GCL: Structural Commonsense Driven Graph Contrastive Learning

2025-07-09 · Dongxiao He, Yongqi Huang, Jitao Zhao, Xiaobao Wang 외 arxiv

Graph Contrastive Learning (GCL) is a widely adopted approach in self-supervised graph representation learning, applying contrastive objectives to produce effective representations. However, current GCL methods primarily…

Graph Representation LearningContrastive Learning

Learning from Missing Relations: Contrastive Learning with Commonsense Knowledge Graphs for Commonsense Inference

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Commonsense inference poses a unique challenge to reason and generate the physical, social, and causal conditions of a given event. Existing approaches to commonsense inference utilize commonsense transformers, which are…

Contrastive LearningDiversityKnowledge Graphs

Learning from Missing Relations: Contrastive Learning with Commonsense Knowledge Graphs for Commonsense Inference

2022-05-01 · Findings (ACL) 2022 5 · Yong-Ho Jung, Jun-Hyung Park, Joon-Young Choi, Mingyu Lee 외

Commonsense inference poses a unique challenge to reason and generate the physical, social, and causal conditions of a given event. Existing approaches to commonsense inference utilize commonsense transformers, which are…

Contrastive LearningDiversityKnowledge Graphs