EMNLP Findings2022
MICO: A Multi-alternative Contrastive Learning Framework for Commonsense Knowledge Representation
Ying Su, Zihao Wang, Tianqing Fang, Hongming Zhang, Yangqiu Song, Tong Zhang
摘要
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 con-trastIve 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.
问 Lune
几分钟读透这篇 Paper,不用再花一下午。
Lune 能读完全文,也能读引用它的顶会 Paper,讲清它的结论、证据和局限,每一点都注明出自哪篇 Paper。不用硬啃,也不靠猜。
已有 3 篇顶会 Paper 引用了它。别等审稿人问起,先弄清它们发现了什么。
脉络
- Complex Reasoning over Logical Queries on Commonsense Knowledge Graphs 引用了 PIQA: Reasoning about Physical Commonsense in Natural Language
- Complex Reasoning over Logical Queries on Commonsense Knowledge Graphs 引用了 (Comet-) Atomic 2020: On Symbolic and Neural Commonsense Knowledge Graphs
- (Comet-) Atomic 2020: On Symbolic and Neural Commonsense Knowledge Graphs 引用了 PIQA: Reasoning about Physical Commonsense in Natural Language
- CANDLE: Iterative Conceptualization and Instantiation Distillation from Large Language Models for Commonsense Reasoning 引用了 PIQA: Reasoning about Physical Commonsense in Natural Language
- CANDLE: Iterative Conceptualization and Instantiation Distillation from Large Language Models for Commonsense Reasoning 引用了 Complex Reasoning over Logical Queries on Commonsense Knowledge Graphs
- CANDLE: Iterative Conceptualization and Instantiation Distillation from Large Language Models for Commonsense Reasoning 引用了 (Comet-) Atomic 2020: On Symbolic and Neural Commonsense Knowledge Graphs
- CANDLE: Iterative Conceptualization and Instantiation Distillation from Large Language Models for Commonsense Reasoning 引用了 CAT: A Contextualized Conceptualization and Instantiation Framework for Commonsense Reasoning
- CAT: A Contextualized Conceptualization and Instantiation Framework for Commonsense Reasoning 引用了 PIQA: Reasoning about Physical Commonsense in Natural Language
- GreaseLM: Graph REASoning Enhanced Language Models 引用了 Graph-Based Reasoning over Heterogeneous External Knowledge for Commonsense Question Answering
- GreaseLM: Graph REASoning Enhanced Language Models 引用了 (Comet-) Atomic 2020: On Symbolic and Neural Commonsense Knowledge Graphs
引用它的顶会 Paper3
- CAT: A Contextualized Conceptualization and Instantiation Framework for Commonsense ReasoningWeiqi Wang, Tianqing Fang, Baixuan Xu, Chun Yi Louis Bo 等ACL 2023 · 13 次引用
- CANDLE: Iterative Conceptualization and Instantiation Distillation from Large Language Models for Commonsense ReasoningWeiqi Wang, Tianqing Fang, Chunyang Li, Haochen Shi 等ACL 2024 · 10 次引用
- Complex Reasoning over Logical Queries on Commonsense Knowledge GraphsTianqing Fang, Zeming Chen, Yangqiu Song, Antoine BosselutACL 2024 · 5 次引用
它引用的 Paper17
- PIQA: Reasoning about Physical Commonsense in Natural LanguageYonatan Bisk, Rowan Zellers, Ronan Le Bras, Jianfeng Gao 等AAAI 2020 · 2,916 次引用
- SimCSE: Simple Contrastive Learning of Sentence EmbeddingsTianyu Gao, Xingcheng Yao, Danqi ChenEMNLP 2021 · 2,496 次引用
- (Comet-) Atomic 2020: On Symbolic and Neural Commonsense Knowledge GraphsJena D. Hwang, Chandra Bhagavatula, Ronan Le Bras, Jeff Da 等AAAI 2021 · 458 次引用
- GreaseLM: Graph REASoning Enhanced Language ModelsXikun Zhang, Antoine Bosselut, Michihiro Yasunaga, Hongyu Ren 等ICLR 2022 · 285 次引用
- Graph-Based Reasoning over Heterogeneous External Knowledge for Commonsense Question AnsweringShangwen Lv, Daya Guo, Jingjing Xu, Duyu Tang 等AAAI 2020 · 224 次引用
相关 Paper
- KE-GCL: Knowledge Enhanced Graph Contrastive Learning for Commonsense Question AnsweringLihui Zhang, Ruifan LiEMNLP Findings 2022 · 7 次引用
- CAR: Conceptualization-Augmented Reasoner for Zero-Shot Commonsense Question AnsweringWeiqi Wang, Tianqing Fang, Wenxuan Ding, Baixuan Xu 等EMNLP Findings 2023 · 19 次引用
- Commonsense Knowledge Graph Completion Via Contrastive Pretraining and Node ClusteringSiwei Wu, Xiangqing Shen, Rui XiaACL Findings 2023 · 7 次引用
- Knowledge-driven Data Construction for Zero-shot Evaluation in Commonsense Question AnsweringKaixin Ma, Filip Ilievski, Jonathan Francis, Yonatan Bisk 等AAAI 2021 · 100 次引用
- VISTA: Visual-Textual Knowledge Graph Representation LearningJaejun Lee, Chanyoung Chung, Hochang Lee, Sungho Jo 等EMNLP Findings 2023 · 58 次引用
