KBQA中用到强化学习的相关论文

最近对用到强化学习的论文进行了简单整理,方便之后查看。我主要是分为两类统计:基于语义解析的方法和基于信息检索的方法。具体的如下:

基于语义解析的KBQA方法

1. 原论文:GraphParser (2014 ACL) 

Large-scale Semantic Parsing without Question-Answer Pairs

提到的有关强化学习的论文:

Reinforcement Learning for Mapping Instructions to Actions (发表年份:2009 发表会议:AFNLP)

        本文提出了一个强化学习的方法,将natural language instructions 映射到 executable actions 序列。我们假设可以使用奖励函数来定义执行操作的质量。在训练过程中,learner重复地为一组文件构建操作序列,执行这些操作,并观察得到的奖励。我们使用一个policy gradient (策略梯度算法)来估计一个对数线性模型的参数来进行操作选择。

        本文在两个领域(Windows故障排除指南和游戏教程)应用此方法解释说明 。当需要少量或者没有标注的训练样例时,此方法能比得上监督学习。

2. 原论文:TextRay(2019 CIKM)

Large-scale Semantic Parsing without Question-Answer Pairs

提到的有关强化学习的论文:

​​​​​​Go for a walk and arrive at the answer: Reasoning over paths in knowledge bases using reinforcement learning (2017 arXiv)

DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoning (2017 EMNLP)

3.  原论文:SSRP(2019 IJCAI)

Neural Program Induction for KBQA Without Gold Programs or Query Annotations

提到的有关强化学习的论文:

Leveraging grammar and reinforcement learning for neural program synthesis (2018 CoRR)

Robust distant supervision relation extraction via deep reinforcement learning(2018 ACL)

Simple statistical gradient-following algorithms for connectionist reinforcement learning(1992)

 4. 原论文:FullModel (2019 IJCAI)

Knowledge Base Question Answering with Topic Units

提到的有关强化学习的论文:

Simple statistical gradient-following algorithms for connectionist reinforcement learning(1992)

5. 原论文: UHop(2019 NAACL)

UHop: An Unrestricted-Hop Relation Extraction Framework for Knowledge-Based Question Answering

提到的有关强化学习的论文:

Simple statistical gradient-following algorithms for connectionist reinforcement learning(1992)

DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoning (2017 EMNLP)

​​​​​​Go for a walk and arrive at the answer: Reasoning over paths in knowledge bases using reinforcement learning (2017 arXiv)

6. 原论文: QGG(2020 ACL)

Query Graph Generation for Answering Multi-hop Complex Questions from Knowledge Bases

提到的有关强化学习的论文:

​​​​​​Go for a walk and arrive at the answer: Reasoning over paths in knowledge bases using reinforcement learning (2017 arXiv)

7. 原论文:DAC(2020 CIKM)

Hierarchical Query Graph Generation for Complex Question Answering over Knowledge Graph

提到的有关强化学习的论文:

Hierarchical deep reinforcement learning: Integrating temporal abstraction  and intrinsic motivation (2016)

Human-level control through deep reinforcement learning(2015 Nature)

Composite Task-Completion Dialogue Policy Learning via Hierarchical Deep Reinforcement Learning (2017 EMNLP)

Intrinsically  motivated reinforcement learning (2005)

Reinforcement learning: An introduction  (2018)

Between MDPs and semi-MDPs: A framework for temporal abstraction in reinforcement learning(1999 Artificial intelligence)

Simple statistical gradient-following algorithms for connectionist reinforcement learning(1992)

8. 原论文:BART-large (2021 EMNLP)

Unseen Entity Handling in Complex Question Answering over KnowledgeBase via Language Generation

提到的有关强化学习的论文:

Neural symbolic machines: Learning semantic parsers on freebase with weak supervision    (2017 ACL)

Learning to decompose compound questions with reinforcement learning (2019)

9. 原论文:CWQ(2018 NAACL)

The Web as a Knowledge-base for Answering Complex Questions

提到的有关强化学习的论文:

Ask the right questions: Active question reformulation with reinforcement learning

(2017 arXiv)

From language to programs: Bridging reinforcement learning and maximum marginal likelihood (2017 ACL)

Seq2sql: Generating structured queries from natural language using reinforcement learning

(2017 arXiv)

10. 原论文:MULTIQUE(2020)

Answering Complex Questions by Combining Information from Curated and Extracted Knowledge Bases

提到的有关强化学习的论文:

DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoning (2017 EMNLP)

​​​​​​Go for a walk and arrive at the answer: Reasoning over paths in knowledge bases using reinforcement learning (2017 arXiv)

11. 原论文:AMR解析(2020)

Question Answering over Knowledge Bases by Leveraging Semantic Parsing and Neuro-Symbolic Reasoning

提到的有关强化学习的论文:

Rewarding Smatch: Transition-Based AMR Parsing with Reinforcement Learning.(2019 arXiv)

12. 原论文:Computer-Programmer(2017 ACL)

Neural Symbolic Machines: Learning Semantic Parsers on Freebase with Weak Supervision

提到的有关强化学习的论文:

Deep reinforcement learning for dialogue generation(2016 arXiv)

Reinforcement Learning: An Introduction.(1998 MA)

Reinforcement learning neural turing machines(2015 arXiv)

Simple statistical gradient-following algorithms for connectionist reinforcement learning(1992)

13. 原论文:CBR(2021)

Case-Based Reasoning for Natural Language Queries over Knowledge Bases

提到的有关强化学习的论文:

Seq2sql: Generating structured queries from natural language using reinforcement learning (2017 arXiv)

基于信息检索的KBQA方法

14. 原论文:ReifKB(2020 arXiv)

SCALABLE NEURAL METHODS FOR REASONING WITH A SYMBOLIC KNOWLEDGE BASE

提到的有关强化学习的论文:

​​​​​​Go for a walk and arrive at the answer: Reasoning over paths in knowledge bases using reinforcement learning (2017 arXiv)

DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoning (2017 EMNLP)

Seq2sql: Generating structured queries from natural language using reinforcement learning (2017 arXiv)

15. 原论文:Rigel-E2E(2021 EMNLP)

End-to-End Entity Resolution and Question Answering Using Differentiable Knowledge Graphs
提到的有关强化学习的论文:

Less is more: Data-efficient complex question answering over knowledge bases.(2020)

Learning to generalize from sparse and underspecified rewards (2019 PMLR)

16. 原论文:VRN(2017 arXiv)

Variational Reasoning for Question Answering with Knowledge Graph

提到的有关强化学习的论文:

Simple statistical gradient-following algorithms for connectionist reinforcement learning(1992)

17. 原论文: IRN(2018 COLING)

An Interpretable Reasoning Network for Multi-Relation Question Answering

提到的有关强化学习的论文:

Coupling distributed and symbolic execution for natural language queries(2017 NSM)
18. 原论文: GRAFT-Net(2018 EMNLP)

Open Domain Question Answering Using Early Fusion of Knowledge Bases and Text

提到的有关强化学习的论文:

​​​​​​Go for a walk and arrive at the answer: Reasoning over paths in knowledge bases using reinforcement learning (2017 arXiv)

R3: Reinforced reader-ranker for open-domain question answering (2018 AAAI)
19. 原论文: PullNet(2019 EMNLP)
PullNet: Open Domain Question Answering with Iterative Retrieval on Knowledge Bases and Text
提到的有关强化学习的论文:

​​​​​​Go for a walk and arrive at the answer: Reasoning over paths in knowledge bases using reinforcement learning (2017 arXiv)

R3: Reinforced reader-ranker for open-domain question answering (2018 AAAI)

20. 原论文: SRN(2020 WSDM)
Stepwise Reasoning for Multi-Relation Question Answering over Knowledge Graph with Weak Supervision

具体问题:当遇到有多个关系的问题时,现存的基于嵌入的方法将考虑以主题实体为中心的整个子图,但这会导致高的时间复杂度。与此同时,由于数据标注的高成本,对于一个复杂的问题,要一步一步地给出答案是不现实的,只有最后的答案才会被标记 用作弱监督

SRN将multi-relation 问答转化为序列决策问题。模型在知识图谱上搜索有效路径获取答案,并利用束搜索减少候选路径的数量。与此同时,基于注意力机制和神经网络,策略梯度可以在三元组选择上增强给定问题不同部分的独特影响。此外,为了缓解由弱监督带来的延迟和稀疏奖励问题,提出来一个potential-based reward shping strategy,从而加快了训练算法的收敛速度,提高了模型的性能。

提到的有关强化学习的论文:
​​​​​​ Go for a walk and arrive at the answer: Reasoning over paths in knowledge bases using reinforcement learning (2017 arXiv)
Reinforcement Learning: An Introduction.(1998 MA)
Simple statistical gradient-following algorithms for connectionist reinforcement learning(1992)

DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoning (2017 EMNLP) 

21. 原论文: NSM(2021 WSDM)
Improving Multi-hop Knowledge Base Question Answering by Learning Intermediate Supervision Signals

多跳问答算法只能收到最终答案的反馈,缺乏中间步骤的监督信号。本文提出了teacher-student 方法 。Student network目的是找到query的正确答案,teacher network目的是学习中间的监督信号(主要体现在实体消歧)以提升student network的推理能力。重点创新是在teacher network的双向推理(从主题实体到答案实体 和  从答案实体到主题实体)。

Student network 是基于Neural State Machine(NSM)实现的,NSM最先在2019年的视觉问答中使用过。Teacher network是通过加入双向推理机制修改了NSM的结构。

提到的有关强化学习的论文:
​​​​​​ Go for a walk and arrive at the answer: Reasoning over paths in knowledge bases using reinforcement learning (2017 arXiv)
Multi-Hop Knowledge Graph Reasoning with Reward Shaping(EMNLP 2018 )
Stepwise Reasoning for Multi-Relation Question Answering over Knowledge Graph with Weak Supervision(2020 WSDM) 

你可能感兴趣的:(KBQA,nlp,自然语言处理,人工智能,知识图谱,深度学习)