Context-aware Path Ranking for Knowledge Base Completion
Sahisnu Mazumder,Bing Liu +1 more
TL;DR: Zhang et al. as mentioned in this paper proposed a Context-Aware Path Ranking (C-PR) algorithm, which learns global semantics of entities in the knowledge base using word embedding and leverages the knowledge of entity semantics to enumerate contextually relevant paths using bidirectional random walk.
read more
Abstract: Knowledge base (KB) completion aims to infer missing facts from existing ones in a KB. Among various approaches, path ranking (PR) algorithms have received increasing attention in recent years. PR algorithms enumerate paths between entity pairs in a KB and use those paths as features to train a model for missing fact prediction. Due to their good performances and high model interpretability, several methods have been proposed. However, most existing methods suffer from scalability (high RAM consumption) and feature explosion (trains on an exponentially large number of features) problems. This paper proposes a Context-aware Path Ranking (C-PR) algorithm to solve these problems by introducing a selective path exploration strategy. C-PR learns global semantics of entities in the KB using word embedding and leverages the knowledge of entity semantics to enumerate contextually relevant paths using bidirectional random walk. Experimental results on three large KBs show that the path features (fewer in number) discovered by C-PR not only improve predictive performance but also are more interpretable than existing baselines.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
•Posted Content
An overview of embedding models of entities and relationships for knowledge base completion.
Dat Quoc Nguyen
- 23 Mar 2017
TL;DR: This paper serves as a comprehensive overview of embedding models of entities and relationships for knowledge base completion, summarizing up-to-date experimental results on standard benchmark datasets.
106
•Dissertation
Relations에 關한 硏究
李應子.
- 01 Jan 1972
Abstract: A double category of relations is essentially a cartesian equipment with strong, discrete and functorial tabulators and for which certain local products satisfy a Frobenius Law. A double category of relations is equivalent to a double category whose proarrows are relations on some ordinary category admitting a proper and stable factorization system. This characterization is based closely on the recent characterization of double categories of spans due to Aleiferi. The overall development can be viewed as a double-categorical version of that of the notion of a"tabular allegory"or that of a"functionally complete bicategory of relations."
•Journal Article
Don't I count?
Eileen Amari-Vaught,Wayne Vaught +1 more
TL;DR: A seventy-year-old woman with metastatic breast cancer undergoing monthly chemotherapy treatments, her granddaughter, Louise, visits her several times a week and helps her do things she can no longer do for herself, but finds that Alice requires more frequent help of every kind.
50
•Posted Content
Towards a Continuous Knowledge Learning Engine for Chatbots.
TL;DR: This paper proposes to build a general knowledge learning engine for chatbots to enable them to continuously and interactively learn new knowledge during conversations and proposes a novel technique called lifelong interactive learning and inference (LiLi) to solve it.
31
Lifelong and Interactive Learning of Factual Knowledge in Dialogues
TL;DR: This article proposed an engine for Continuous and Interactive Learning of Knowledge (CILK) for dialogue systems to give them the ability to continuously and interactively learn and infer new knowledge during conversations.
31
References
•Proceedings Article
Efficient Estimation of Word Representations in Vector Space
Tomas Mikolov,Kai Chen,Greg S. Corrado,Jeffrey Dean +3 more
- 16 Jan 2013
TL;DR: Two novel model architectures for computing continuous vector representations of words from very large data sets are proposed and it is shown that these vectors provide state-of-the-art performance on the authors' test set for measuring syntactic and semantic word similarities.
27.5K
•Proceedings Article
Distributed Representations of Words and Phrases and their Compositionality
Tomas Mikolov,Ilya Sutskever,Kai Chen,Greg S. Corrado,Jeffrey Dean +4 more
- 05 Dec 2013
TL;DR: This paper presents a simple method for finding phrases in text, and shows that learning good vector representations for millions of phrases is possible and describes a simple alternative to the hierarchical softmax called negative sampling.
•Posted Content
Distributed Representations of Words and Phrases and their Compositionality
TL;DR: In this paper, the Skip-gram model is used to learn high-quality distributed vector representations that capture a large number of precise syntactic and semantic word relationships and improve both the quality of the vectors and the training speed.
WordNet: a lexical database for English
TL;DR: WordNet1 provides a more effective combination of traditional lexicographic information and modern computing, and is an online lexical database designed for use under program control.
16.9K
•Proceedings Article
Translating Embeddings for Modeling Multi-relational Data
Antoine Bordes,Nicolas Usunier,Alberto Garcia-Duran,Jason Weston,Oksana Yakhnenko +4 more
- 05 Dec 2013
TL;DR: TransE is proposed, a method which models relationships by interpreting them as translations operating on the low-dimensional embeddings of the entities, which proves to be powerful since extensive experiments show that TransE significantly outperforms state-of-the-art methods in link prediction on two knowledge bases.
Related Papers (5)
Ye Xu,Daniel N. Rockmore +1 more
- 02 Nov 2012
Quanyu Dai,Qiang Li,Liang Zhang,Dan Wang +3 more
- 14 Apr 2019