Answering Complex Queries in Knowledge Graphs with Bidirectional
Sequence Encoders
- URL: http://arxiv.org/abs/2004.02596v4
- Date: Thu, 4 Feb 2021 11:23:52 GMT
- Title: Answering Complex Queries in Knowledge Graphs with Bidirectional
Sequence Encoders
- Authors: Bhushan Kotnis, Carolin Lawrence, Mathias Niepert
- Abstract summary: We propose Bi-Directional Query Embedding (BIQE), a method that embeds conjunctive queries with models based on bi-directional attention mechanisms.
We introduce a new dataset for predicting the answer of conjunctive query and conduct experiments that show BIQE significantly outperforming state of the art baselines.
- Score: 22.63481666560029
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Representation learning for knowledge graphs (KGs) has focused on the problem
of answering simple link prediction queries. In this work we address the more
ambitious challenge of predicting the answers of conjunctive queries with
multiple missing entities. We propose Bi-Directional Query Embedding (BIQE), a
method that embeds conjunctive queries with models based on bi-directional
attention mechanisms. Contrary to prior work, bidirectional self-attention can
capture interactions among all the elements of a query graph. We introduce a
new dataset for predicting the answer of conjunctive query and conduct
experiments that show BIQE significantly outperforming state of the art
baselines.
Related papers
- FedCQA: Answering Complex Queries on Multi-Source Knowledge Graphs via
Federated Learning [55.02512821257247]
Complex logical query answering is a challenging task in knowledge graphs (KGs)
Recent approaches are proposed to represent KG entities into embedding vectors and find answers to logical queries from the KGs.
It remains unknown how to answer queries on multi-source KGs.
arXiv Detail & Related papers (2024-02-22T14:57:44Z) - Neural Graph Reasoning: Complex Logical Query Answering Meets Graph
Databases [63.96793270418793]
Complex logical query answering (CLQA) is a recently emerged task of graph machine learning.
We introduce the concept of Neural Graph Database (NGDBs)
NGDB consists of a Neural Graph Storage and a Neural Graph Engine.
arXiv Detail & Related papers (2023-03-26T04:03:37Z) - Logical Message Passing Networks with One-hop Inference on Atomic
Formulas [57.47174363091452]
We propose a framework for complex query answering that decomposes the Knowledge Graph embeddings from neural set operators.
On top of the query graph, we propose the Logical Message Passing Neural Network (LMPNN) that connects the local one-hop inferences on atomic formulas to the global logical reasoning.
Our approach yields the new state-of-the-art neural CQA model.
arXiv Detail & Related papers (2023-01-21T02:34:06Z) - UniKGQA: Unified Retrieval and Reasoning for Solving Multi-hop Question
Answering Over Knowledge Graph [89.98762327725112]
Multi-hop Question Answering over Knowledge Graph(KGQA) aims to find the answer entities that are multiple hops away from the topic entities mentioned in a natural language question.
We propose UniKGQA, a novel approach for multi-hop KGQA task, by unifying retrieval and reasoning in both model architecture and parameter learning.
arXiv Detail & Related papers (2022-12-02T04:08:09Z) - Query2Particles: Knowledge Graph Reasoning with Particle Embeddings [49.64006979045662]
We propose a query embedding method to answer complex logical queries on knowledge graphs with missing edges.
The answer entities are selected according to the similarities between the entity embeddings and the query embedding.
A complex KG query answering method, Q2P, is proposed to retrieve diverse answers from different areas over the embedding space.
arXiv Detail & Related papers (2022-04-27T11:16:08Z) - Semantic Structure based Query Graph Prediction for Question Answering
over Knowledge Graph [5.5332967798665305]
This paper focuses on query graph generation from natural language questions.
Existing approaches for query graph generation ignore the semantic structure of a question.
We develop a novel Structure-BERT to predict the semantic structure of a question.
arXiv Detail & Related papers (2022-04-15T20:35:00Z) - Question-Answer Sentence Graph for Joint Modeling Answer Selection [122.29142965960138]
We train and integrate state-of-the-art (SOTA) models for computing scores between question-question, question-answer, and answer-answer pairs.
Online inference is then performed to solve the AS2 task on unseen queries.
arXiv Detail & Related papers (2022-02-16T05:59:53Z) - Outlining and Filling: Hierarchical Query Graph Generation for Answering
Complex Questions over Knowledge Graph [16.26384829957165]
We propose a new two-stage approach to build query graphs.
In the first stage, the top-$k$ related instances are collected by simple strategies.
In the second stage, a graph generation model performs hierarchical generation.
arXiv Detail & Related papers (2021-11-01T07:08:46Z) - Query Embedding on Hyper-relational Knowledge Graphs [0.4779196219827507]
Multi-hop logical reasoning is an established problem in the field of representation learning on knowledge graphs.
We extend the multi-hop reasoning problem to hyper-relational KGs allowing to tackle this new type of complex queries.
arXiv Detail & Related papers (2021-06-15T14:08:50Z) - Modeling Global Semantics for Question Answering over Knowledge Bases [16.341353183347664]
We present a relational graph convolutional network (RGCN)-based model gRGCN for semantic parsing in KBQA.
Experiments evaluated on benchmarks show that our model outperforms off-the-shelf models.
arXiv Detail & Related papers (2021-01-05T13:51:14Z) - Message Passing Query Embedding [4.035753155957698]
We propose a graph neural network to encode a graph representation of a query.
We show that the model learns entity embeddings that capture the notion of entity type without explicit supervision.
arXiv Detail & Related papers (2020-02-06T17:40:01Z)
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.