KompaRe: A Knowledge Graph Comparative Reasoning System
- URL: http://arxiv.org/abs/2011.03189v1
- Date: Fri, 6 Nov 2020 04:57:37 GMT
- Title: KompaRe: A Knowledge Graph Comparative Reasoning System
- Authors: Lihui Liu, Boxin Du, Heng Ji, Hanghang Tong
- Abstract summary: This paper introduces comparative reasoning over knowledge graphs, which aims to infer the commonality and inconsistency with respect to multiple pieces of clues.
We develop KompaRe, the first of its kind prototype system that provides comparative reasoning capability over large knowledge graphs.
- Score: 85.72488258453926
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Reasoning is a fundamental capability for harnessing valuable insight,
knowledge and patterns from knowledge graphs. Existing work has primarily been
focusing on point-wise reasoning, including search, link predication, entity
prediction, subgraph matching and so on. This paper introduces comparative
reasoning over knowledge graphs, which aims to infer the commonality and
inconsistency with respect to multiple pieces of clues. We envision that the
comparative reasoning will complement and expand the existing point-wise
reasoning over knowledge graphs. In detail, we develop KompaRe, the first of
its kind prototype system that provides comparative reasoning capability over
large knowledge graphs. We present both the system architecture and its core
algorithms, including knowledge segment extraction, pairwise reasoning and
collective reasoning. Empirical evaluations demonstrate the efficacy of the
proposed KompaRe.
Related papers
- Detecting text level intellectual influence with knowledge graph embeddings [0.0]
We collect a corpus of open source journal articles and generate Knowledge Graph representations using the Gemini LLM.
We attempt to predict the existence of citations between sampled pairs of articles using previously published methods and a novel Graph Neural Network based embedding model.
arXiv Detail & Related papers (2024-10-31T15:21:27Z) - Knowledge Graph Extension by Entity Type Recognition [2.8231106019727195]
We propose a novel knowledge graph extension framework based on entity type recognition.
The framework aims to achieve high-quality knowledge extraction by aligning the schemas and entities across different knowledge graphs.
arXiv Detail & Related papers (2024-05-03T19:55:03Z) - Similarity-weighted Construction of Contextualized Commonsense Knowledge
Graphs for Knowledge-intense Argumentation Tasks [17.438104235331085]
We present a new unsupervised method for constructing Contextualized Commonsense Knowledge Graphs (CCKGs)
Our work goes beyond context-insensitive knowledge extractions by computing semantic similarity between KG triplets and textual arguments.
We demonstrate the effectiveness of CCKGs in a knowledge-insensitive argument quality rating task, outperforming strong baselines and rivaling a GPT-3 based system.
arXiv Detail & Related papers (2023-05-15T09:52:36Z) - Knowledge Graph Reasoning with Logics and Embeddings: Survey and
Perspective [35.1522867772523]
Knowledge graph (KG) reasoning is becoming increasingly popular in both academia and industry.
A promising direction is to integrate both logic-based and embedding-based methods.
arXiv Detail & Related papers (2022-02-15T13:59:54Z) - Knowledge Graph Augmented Network Towards Multiview Representation
Learning for Aspect-based Sentiment Analysis [96.53859361560505]
We propose a knowledge graph augmented network (KGAN) to incorporate external knowledge with explicitly syntactic and contextual information.
KGAN captures the sentiment feature representations from multiple perspectives, i.e., context-, syntax- and knowledge-based.
Experiments on three popular ABSA benchmarks demonstrate the effectiveness and robustness of our KGAN.
arXiv Detail & Related papers (2022-01-13T08:25:53Z) - Conditional Attention Networks for Distilling Knowledge Graphs in
Recommendation [74.14009444678031]
We propose Knowledge-aware Conditional Attention Networks (KCAN) to incorporate knowledge graph into a recommender system.
We use a knowledge-aware attention propagation manner to obtain the node representation first, which captures the global semantic similarity on the user-item network and the knowledge graph.
Then, by applying a conditional attention aggregation on the subgraph, we refine the knowledge graph to obtain target-specific node representations.
arXiv Detail & Related papers (2021-11-03T09:40:43Z) - Fact-driven Logical Reasoning for Machine Reading Comprehension [82.58857437343974]
We are motivated to cover both commonsense and temporary knowledge clues hierarchically.
Specifically, we propose a general formalism of knowledge units by extracting backbone constituents of the sentence.
We then construct a supergraph on top of the fact units, allowing for the benefit of sentence-level (relations among fact groups) and entity-level interactions.
arXiv Detail & Related papers (2021-05-21T13:11:13Z) - Neural, Symbolic and Neural-Symbolic Reasoning on Knowledge Graphs [9.708996828407384]
Knowledge graph reasoning supports machine learning applications such as information extraction, information retrieval, and recommendation.
Since knowledge graphs can be viewed as the discrete symbolic representations of knowledge, reasoning on knowledge graphs can naturally leverage the symbolic techniques.
Recent advances of deep learning promote neural reasoning on knowledge graphs, which is robust to the ambiguous and noisy data, but lacks interpretability compared to symbolic reasoning.
arXiv Detail & Related papers (2020-10-12T04:28:57Z) - A Heterogeneous Graph with Factual, Temporal and Logical Knowledge for
Question Answering Over Dynamic Contexts [81.4757750425247]
We study question answering over a dynamic textual environment.
We develop a graph neural network over the constructed graph, and train the model in an end-to-end manner.
arXiv Detail & Related papers (2020-04-25T04:53:54Z) - A Survey on Knowledge Graphs: Representation, Acquisition and
Applications [89.78089494738002]
We review research topics about 1) knowledge graph representation learning, 2) knowledge acquisition and completion, 3) temporal knowledge graph, and 4) knowledge-aware applications.
For knowledge acquisition, especially knowledge graph completion, embedding methods, path inference, and logical rule reasoning, are reviewed.
We explore several emerging topics, including meta learning, commonsense reasoning, and temporal knowledge graphs.
arXiv Detail & Related papers (2020-02-02T13:17:31Z)
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.