UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models

• URL: http://arxiv.org/abs/2201.05966v2
• Date: Thu, 20 Jan 2022 03:20:45 GMT
• Title: UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models
• Authors: Tianbao Xie, Chen Henry Wu, Peng Shi, Ruiqi Zhong, Torsten Scholak, Michihiro Yasunaga, Chien-Sheng Wu, Ming Zhong, Pengcheng Yin, Sida I. Wang, Victor Zhong, Bailin Wang, Chengzu Li, Connor Boyle, Ansong Ni, Ziyu Yao, Dragomir Radev, Caiming Xiong, Lingpeng Kong, Rui Zhang, Noah A. Smith, Luke Zettlemoyer, Tao Yu
• Abstract summary: We propose the SKG framework, which unifies 21 SKG tasks into a text-to-text format. We show that UnifiedSKG achieves state-of-the-art performance on almost all of the 21 tasks. We also use UnifiedSKG to conduct a series of experiments on structured knowledge encoding variants across SKG tasks.
• Score: 170.88745906220174
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Structured knowledge grounding (SKG) leverages structured knowledge to complete user requests, such as semantic parsing over databases and question answering over knowledge bases. Since the inputs and outputs of SKG tasks are heterogeneous, they have been studied separately by different communities, which limits systematic and compatible research on SKG. In this paper, we overcome this limitation by proposing the SKG framework, which unifies 21 SKG tasks into a text-to-text format, aiming to promote systematic SKG research, instead of being exclusive to a single task, domain, or dataset. We use UnifiedSKG to benchmark T5 with different sizes and show that T5, with simple modifications when necessary, achieves state-of-the-art performance on almost all of the 21 tasks. We further demonstrate that multi-task prefix-tuning improves the performance on most tasks, largely improving the overall performance. UnifiedSKG also facilitates the investigation of zero-shot and few-shot learning, and we show that T0, GPT-3, and Codex struggle in zero-shot and few-shot learning for SKG. We also use UnifiedSKG to conduct a series of controlled experiments on structured knowledge encoding variants across SKG tasks. UnifiedSKG is easily extensible to more tasks, and it is open-sourced at https://github.com/hkunlp/unifiedskg Latest collections at https://unifiedskg.com.

Related papers

• Generate-on-Graph: Treat LLM as both Agent and KG in Incomplete Knowledge Graph Question Answering [90.30473970040362]
  We propose a training-free method called Generate-on-Graph (GoG) that can generate new factual triples while exploring on Knowledge Graphs (KGs) Specifically, we propose a selecting-generating-answering framework, which not only treat the LLM as an agent to explore on KGs, but also treat it as a KG to generate new facts based on the explored subgraph.
  arXiv  Detail & Related papers  (2024-04-23T04:47:22Z)
• Task-Oriented GNNs Training on Large Knowledge Graphs for Accurate and Efficient Modeling [5.460112864687281]
  This paper proposes KG-TOSA, an approach to automate the TOSG extraction for task-oriented HGNN training on a large Knowledge Graph (KG) KG-TOSA helps state-of-the-art HGNN methods reduce training time and memory usage by up to 70% while improving the model performance, e.g., accuracy and inference time.
  arXiv  Detail & Related papers  (2024-03-09T01:17:26Z)
• KG-GPT: A General Framework for Reasoning on Knowledge Graphs Using Large Language Models [18.20425100517317]
  We propose KG-GPT, a framework leveraging large language models for tasks employing knowledge graphs. KG-GPT comprises three steps: Sentence, Graph Retrieval, and Inference, each aimed at partitioning sentences, retrieving relevant graph components, and deriving logical conclusions. We evaluate KG-GPT using KG-based fact verification and KGQA benchmarks, with the model showing competitive and robust performance, even outperforming several fully-supervised models.
  arXiv  Detail & Related papers  (2023-10-17T12:51:35Z)
• Search to Pass Messages for Temporal Knowledge Graph Completion [97.40256786473516]
  We propose to use neural architecture search (NAS) to design data-specific message passing architecture for temporal knowledge graphs (TKGs) completion. In particular, we develop a generalized framework to explore topological and temporal information in TKGs. We adopt a search algorithm, which trains a supernet structure by sampling single path for efficient search with less cost.
  arXiv  Detail & Related papers  (2022-10-30T04:05:06Z)
• Reasoning over Multi-view Knowledge Graphs [59.99051368907095]
  ROMA is a novel framework for answering logical queries over multi-view KGs. It scales up to KGs of large sizes (e.g., millions of facts) and fine-granular views. It generalizes to query structures and KG views that are unobserved during training.
  arXiv  Detail & Related papers  (2022-09-27T21:32:20Z)
• Syntax Controlled Knowledge Graph-to-Text Generation with Order and Semantic Consistency [10.7334441041015]
  Knowledge graph-to-text (KG-to-text) generation aims to generate easy-to-understand sentences from the knowledge graph. In this paper, we optimize the knowledge description order prediction under the order supervision extracted from the caption. We incorporate the Part-of-Speech (POS) syntactic tags to constrain the positions to copy words from the KG.
  arXiv  Detail & Related papers  (2022-07-02T02:42:14Z)
• Generalized Few-shot Semantic Segmentation [68.69434831359669]
  We introduce a new benchmark called Generalized Few-Shot Semantic (GFS-Seg) to analyze the ability of simultaneously segmenting the novel categories. It is the first study showing that previous representative state-of-the-art generalizations fall short in GFS-Seg. We propose the Context-Aware Prototype Learning (CAPL) that significantly improves performance by 1) leveraging the co-occurrence prior knowledge from support samples, and 2) dynamically enriching contextual information to the conditioned, on the content of each query image.
  arXiv  Detail & Related papers  (2020-10-11T10:13:21Z)
• Multilingual Knowledge Graph Completion via Ensemble Knowledge Transfer [43.453915033312114]
  Predicting missing facts in a knowledge graph (KG) is a crucial task in knowledge base construction and reasoning. We propose KEnS, a novel framework for embedding learning and ensemble knowledge transfer across a number of language-specific KGs. Experiments on five real-world language-specific KGs show that KEnS consistently improves state-of-the-art methods on KG completion.
  arXiv  Detail & Related papers  (2020-10-07T04:54:03Z)
• Cross-lingual Entity Alignment with Incidental Supervision [76.66793175159192]
  We propose an incidentally supervised model, JEANS, which jointly represents multilingual KGs and text corpora in a shared embedding scheme. Experiments on benchmark datasets show that JEANS leads to promising improvement on entity alignment with incidental supervision.
  arXiv  Detail & Related papers  (2020-05-01T01:53:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.