Deep Bidirectional Language-Knowledge Graph Pretraining
Michihiro Yasunaga, Antoine Bosselut, Hongyu Ren, Xikun Zhang, Christopher D. Manning, Percy Liang, Jure Leskovec
摘要
Pretraining a language model (LM) on text has been shown to help various downstream NLP tasks. Recent works show that a knowledge graph (KG) can complement text data, offering structured background knowledge that provides a useful scaffold for reasoning. However, these works are not pretrained to learn a deep fusion of the two modalities at scale, limiting the potential to acquire fully joint representations of text and KG. Here we propose DRAGON (Deep Bidirectional Language-Knowledge Graph Pretraining), a self-supervised method to pretrain a deeply joint language-knowledge foundation model from text and KG at scale. Specifically, our model takes pairs of text segments and relevant KG subgraphs as input and bidirectionally fuses information from both modalities. We pretrain this model by unifying two self-supervised reasoning tasks, masked language modeling and KG link prediction. DRAGON outperforms existing LM and LM+KG models on diverse downstream tasks including question answering across general and biomedical domains, with +5% absolute gain on average. In particular, DRAGON achieves strong performance on complex reasoning about language and knowledge (+10% on questions involving long contexts or multi-step reasoning) and low-resource QA (+8% on OBQA and RiddleSense), and new state-of-the-art results on various BioNLP tasks. Our code and trained models are available at https://github.com/michiyasunaga/dragon . Glamping GNN 1st Layer Glamping GNN Final Layer camp trip beach school beach RoBERTa: A. camp (✗) GreaseLM: C. camp (✗) Glamping: B. school (✓) school trip Glamping GNN 1st Layer Glamping GNN Final Layer garage trip beach school beach garage movie Glamping GNN 1st Layer Glamping GNN Final Layer entertain ment station movie Glamping GNN 1st Layer Glamping GNN Final Layer live movie movie entertain ment station live Model Prediction RoBERTa: B. school (✗) GreaseLM: B. school (✗) Glamping: C. beach (✓) Model Prediction B. movie theater (✓) GreaseLM: B. movie theater (✓) Glamping: B. movie theater (✓) Model Prediction B. movie theater (✗) GreaseLM: B. movie theater (✗)
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了最后一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper44
- HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language ModelsBernal Jimenez Gutierrez, Yiheng Shu, Yu Gu, Michihiro Yasunaga 等NeurIPS 2024 · 被引用 395 次
- Knowledge Graph Prompting for Multi-Document Question AnsweringYu Wang, Nedim Lipka, Ryan A. Rossi, Alexa F. Siu 等AAAI 2024 · 被引用 290 次
- UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language ModelsTianbao Xie, Chen Henry Wu, Peng Shi, Ruiqi Zhong 等EMNLP 2022 · 被引用 222 次
- MediQ: Question-Asking LLMs and a Benchmark for Reliable Interactive Clinical ReasoningShuyue Stella Li, Vidhisha Balachandran, Shangbin Feng, Jonathan Ilgen 等NeurIPS 2024 · 被引用 215 次
- Talk like a Graph: Encoding Graphs for Large Language ModelsBahare Fatemi, Jonathan Halcrow, Bryan PerozziICLR 2024 · 被引用 194 次
它引用的顶会 Paper16
- Language Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah 等NeurIPS 2020 · 被引用 64,255 次
- Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsJason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma 等NeurIPS 2022 · 被引用 22,562 次
- Retrieval-Augmented Generation for Knowledge-Intensive NLP TasksPatrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni 等NeurIPS 2020 · 被引用 19,162 次
- PIQA: Reasoning about Physical Commonsense in Natural LanguageYonatan Bisk, Rowan Zellers, Ronan Le Bras, Jianfeng Gao 等AAAI 2020 · 被引用 2,916 次
- Improving Language Models by Retrieving from Trillions of TokensSebastian Borgeaud, Arthur Mensch, Jordan Hoffmann, Trevor Cai 等ICML 2022 · 被引用 1,629 次
相关 Paper
- LinkBERT: Pretraining Language Models with Document LinksMichihiro Yasunaga, Jure Leskovec, Percy LiangACL 2022 · 被引用 463 次
- Exploiting Structured Knowledge in Text via Graph-Guided Representation LearningTao Shen, Yi Mao, Pengcheng He, Guodong Long 等EMNLP 2020 · 被引用 60 次
- ReasoningLM: Enabling Structural Subgraph Reasoning in Pre-trained Language Models for Question Answering over Knowledge GraphJinhao Jiang, Kun Zhou, Wayne Xin Zhao, Yaliang Li 等EMNLP 2023 · 被引用 26 次
- GreaseLM: Graph REASoning Enhanced Language ModelsXikun Zhang, Antoine Bosselut, Michihiro Yasunaga, Hongyu Ren 等ICLR 2022 · 被引用 285 次
- JAKET: Joint Pre-training of Knowledge Graph and Language UnderstandingDonghan Yu, Chenguang Zhu, Yiming Yang, Michael ZengAAAI 2022 · 被引用 171 次
