Scalable Rule Learning via Learning Representation

Omran, Pouya Ghiasnezhad; Wang, Kewen; Wang, Zhe

doi:10.24963/ijcai.2018/297

Cited by 30 publications

(12 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Rule-based reasoning can be divided into two categories, namely neuralbased models and rule mining models. Among them, neural-based models ( Rocktäschel and Riedel, 2017;Sadeghian et al, 2019;Minervini et al, 2020)) give the corresponding rules while performing triple completion, while rule mining models ( (Galárraga et al, 2015;Omran et al, 2018;Ho et al, 2018;Meilicke et al, 2019)) first mine the rules and then use them for completion.…”

Section: Rule-based Reasoningmentioning

confidence: 99%

Is Multi-Hop Reasoning Really Explainable? Towards Benchmarking Reasoning Interpretability

Lv¹,

Cao²,

Hou³

et al. 2021

Preprint

View full text Add to dashboard Cite

Multi-hop reasoning has been widely studied in recent years to obtain more interpretable link prediction. However, we find in experiments that many paths given by these models are actually unreasonable, while little works have been done on interpretability evaluation for them. In this paper, we propose a unified framework to quantitatively evaluate the interpretability of multi-hop reasoning models so as to advance their development. In specific, we define three metrics including path recall, local interpretability, and global interpretability for evaluation, and design an approximate strategy to calculate them using the interpretability scores of rules. Furthermore, we manually annotate all possible rules and establish a Benchmark to detect the Interpretability of Multi-hop Reasoning (BIMR). In experiments, we run nine baselines on our benchmark. The experimental results show that the interpretability of current multi-hop reasoning models is less satisfactory and is still far from the upper bound given by our benchmark. Moreover, the rule-based models outperform the multi-hop reasoning models in terms of performance and interpretability, which points to a direction for future research, i.e., we should investigate how to better incorporate rule information into the multi-hop reasoning model. Our codes and datasets can be obtained from https://github.com/THU-KEG/ BIMR.

show abstract

Section: Rule-based Reasoningmentioning

confidence: 99%

Is Multi-Hop Reasoning Really Explainable? Towards Benchmarking Reasoning Interpretability

Lv¹,

Cao²,

Hou³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…The quality of rule learning is evaluated with the number of high quality rule (HQr) and their percentage. The quality of rules are evaluated by head coverage(HC) which is commonly used in pervious work, such as [10] and [29]. Head 5 we run AMIE+ code from https://www.mpi-inf.mpg.de/departments/databases-andinformation-systems/research/yago-naga/amie/ coverage for rule rul is defined as follows: Table 6.…”

Section: Rule Evaluationmentioning

confidence: 99%

“…Embeddings are also used to help rule learning and are used for different purposes. Some utilize embeddings to guide and prune the search for candidate rules [29]. Some make embeddings to complete the knowledge graph during rule learning [16].…”

Section: Rule Learningmentioning

confidence: 99%

Iteratively Learning Embeddings and Rules for Knowledge Graph Reasoning

Zhang

Paudel

Wang

et al. 2019

The World Wide Web Conference

133

View full text Add to dashboard Cite

Reasoning is essential for the development of large knowledge graphs, especially for completion, which aims to infer new triples based on existing ones. Both rules and embeddings can be used for knowledge graph reasoning and they have their own advantages and difficulties. Rule-based reasoning is accurate and explainable but rule learning with searching over the graph always suffers from efficiency due to huge search space. Embedding-based reasoning is more scalable and efficient as the reasoning is conducted via computation between embeddings, but it has difficulty learning good representations for sparse entities because a good embedding relies heavily on data richness. Based on this observation, in this paper we explore how embedding and rule learning can be combined together and complement each other's difficulties with their advantages. We propose a novel framework IterE iteratively learning embeddings and rules, in which rules are learned from embeddings with proper pruning strategy and embeddings are learned from existing triples and new triples inferred by rules. Evaluations on embedding qualities of IterE show that rules help improve the quality of sparse entity embeddings and their link prediction results. We also evaluate the efficiency of rule learning and quality of rules from IterE compared with AMIE+, showing that IterE is capable of generating high quality rules more efficiently. Experiments show * Work done while at UZH.

show abstract

“…Consistency checking depends on domain knowledge of a specific task for constraint and rule definition, while the mined constraints and rules are often weak in modeling local context for disambiguation. Semantic embedding methods are good at modeling contextual semantics in a vector space, but are computationally expensive when learning from large KBs [30] and suffer from low robustness when dealing with real world KBs that are often noisy and sparse [35].…”

Section: Assertion Validationmentioning

confidence: 99%

Correcting Knowledge Base Assertions

Chen

Horrocks

et al. 2020

Proceedings of the Web Conference 2020

View full text Add to dashboard Cite

The usefulness and usability of knowledge bases (KBs) is often limited by quality issues. One common issue is the presence of erroneous assertions, often caused by lexical or semantic confusion. We study the problem of correcting such assertions, and present a general correction framework which combines lexical matching, semantic embedding, soft constraint mining and semantic consistency checking. The framework is evaluated using DBpedia and an enterprise medical KB.

show abstract

Scalable Rule Learning via Learning Representation

Cited by 30 publications

References 5 publications

Is Multi-Hop Reasoning Really Explainable? Towards Benchmarking Reasoning Interpretability

Is Multi-Hop Reasoning Really Explainable? Towards Benchmarking Reasoning Interpretability

Iteratively Learning Embeddings and Rules for Knowledge Graph Reasoning

Correcting Knowledge Base Assertions

Contact Info

Product

Resources

About