Graph Reasoning for Question Answering with Triplet Retrieval
- URL: http://arxiv.org/abs/2305.18742v1
- Date: Tue, 30 May 2023 04:46:28 GMT
- Title: Graph Reasoning for Question Answering with Triplet Retrieval
- Authors: Shiyang Li, Yifan Gao, Haoming Jiang, Qingyu Yin, Zheng Li, Xifeng
Yan, Chao Zhang, Bing Yin
- Abstract summary: We propose a simple yet effective method to retrieve the most relevant triplets from knowledge graphs (KGs)
Our method can outperform state-of-the-art up to 4.6% absolute accuracy.
- Score: 33.454090126152714
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Answering complex questions often requires reasoning over knowledge graphs
(KGs). State-of-the-art methods often utilize entities in questions to retrieve
local subgraphs, which are then fed into KG encoder, e.g. graph neural networks
(GNNs), to model their local structures and integrated into language models for
question answering. However, this paradigm constrains retrieved knowledge in
local subgraphs and discards more diverse triplets buried in KGs that are
disconnected but useful for question answering. In this paper, we propose a
simple yet effective method to first retrieve the most relevant triplets from
KGs and then rerank them, which are then concatenated with questions to be fed
into language models. Extensive results on both CommonsenseQA and OpenbookQA
datasets show that our method can outperform state-of-the-art up to 4.6%
absolute accuracy.
Related papers
- Multi-hop Question Answering over Knowledge Graphs using Large Language Models [1.8130068086063336]
We evaluate the capability of (LLMs) to answer questions over Knowledge graphs that involve multiple hops.
We show that depending upon the size and nature of the KG we need different approaches to extract and feed the relevant information to an LLM.
arXiv Detail & Related papers (2024-04-30T03:31:03Z) - 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) - 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) - 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) - Improving Question Answering over Knowledge Graphs Using Graph
Summarization [0.2752817022620644]
Key idea is to represent questions and entities of a Knowledge Graph as low-dimensional embeddings.
We propose a graph summarization technique using Recurrent Convolutional Neural Network (RCNN) and GCN.
The proposed graph summarization technique can be used to tackle the issue that KGQAs cannot answer questions with an uncertain number of answers.
arXiv Detail & Related papers (2022-03-25T10:57:10Z) - Knowledge Base Question Answering by Case-based Reasoning over Subgraphs [81.22050011503933]
We show that our model answers queries requiring complex reasoning patterns more effectively than existing KG completion algorithms.
The proposed model outperforms or performs competitively with state-of-the-art models on several KBQA benchmarks.
arXiv Detail & Related papers (2022-02-22T01:34:35Z) - Graph-augmented Learning to Rank for Querying Large-scale Knowledge
Graph [34.774049199809426]
Knowledge graph question answering (i.e., KGQA) based on information retrieval aims to answer a question by retrieving answer from a large-scale knowledge graph.
We first propose to partition the retrieved KSG to several smaller sub-KSGs via a new subgraph partition algorithm.
We then present a graph-augmented learning to rank model to select the top-ranked sub-KSGs from them.
arXiv Detail & Related papers (2021-11-20T08:27:37Z) - UNIQORN: Unified Question Answering over RDF Knowledge Graphs and
Natural Language Text [26.59527112409611]
Question answering over knowledge graphs and other RDF data has been greatly advanced.
This paper presents a method for complex questions that can seamlessly operate over a mixture of RDF datasets and text corpora.
arXiv Detail & Related papers (2021-08-19T10:50:52Z) - Toward Subgraph-Guided Knowledge Graph Question Generation with Graph
Neural Networks [53.58077686470096]
Knowledge graph (KG) question generation (QG) aims to generate natural language questions from KGs and target answers.
In this work, we focus on a more realistic setting where we aim to generate questions from a KG subgraph and target answers.
arXiv Detail & Related papers (2020-04-13T15:43:22Z)
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.