Long-tail Relation Extraction via Knowledge Graph Embeddings and Graph Convolution Networks

Zhang, Ningyu; Deng, Shumin; Sun, Zhanlin; Wang, Guanying; Chen, Xi; Zhang, Wei; Chen, Huajun

doi:10.18653/v1/n19-1306

Cited by 200 publications

(97 citation statements)

References 38 publications

(56 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similarly, the KBP approaches would be error-sensitive for incidentallyappeared entities, as they cannot handle errors or exceptions well. We note that a few works have begun to study the long-tail phenomenon in KBs, but they tackle different problems, e.g., linking long-tail entities to KBs [8], extracting long-tail relations [54] and verifying facts for long-tail domains [24].…”

Section: Introductionmentioning

confidence: 99%

Open Knowledge Enrichment for Long-tail Entities

Cao

Wang

2020

Proceedings of the Web Conference 2020

View full text Add to dashboard Cite

Knowledge bases (KBs) have gradually become a valuable asset for many AI applications. While many current KBs are quite large, they are widely acknowledged as incomplete, especially lacking facts of long-tail entities, e.g., less famous persons. Existing approaches enrich KBs mainly on completing missing links or filling missing values. However, they only tackle a part of the enrichment problem and lack specific considerations regarding long-tail entities. In this paper, we propose a full-fledged approach to knowledge enrichment, which predicts missing properties and infers true facts of long-tail entities from the open Web. Prior knowledge from popular entities is leveraged to improve every enrichment step. Our experiments on the synthetic and real-world datasets and comparison with related work demonstrate the feasibility and superiority of the approach.

show abstract

Section: Introductionmentioning

confidence: 99%

Open Knowledge Enrichment for Long-tail Entities

Cao

Wang

2020

Proceedings of the Web Conference 2020

View full text Add to dashboard Cite

show abstract

“…Knowledge Graph Completion. KGC can be achieved either by link prediction from knowledge graph [59] or by extracting new relational facts from textual corpus [57]. A variety of link prediction approaches have been proposed to encode entities and relations into a continuous low-dimensional space.…”

Section: Related Workmentioning

confidence: 99%

“…In contrast, [23,29] worked on unsupervised domain adaptation. [58] proposes to take advantage of the knowledge from data-rich classes at the head of the distribution to boost the performance of the data-poor classes at the tail. [10,25] presented adversarial learning algorithms for unsupervised domain adaptation tasks.…”

Section: Related Workmentioning

confidence: 99%

“…Knowledge Graphs (KGs) organize facts in a structured way as triples in the form of <subject, predicate, object>, abridged as (s, p, o), where s and o denote entities and p builds relations between entities. Due to the convenience of building semantic connections between data from various sources, many large-scale KGs have been built in recent years and have led to a broad range of important applications, such as question answering [48], language understanding [60], relational data analytics [57], recommender systems [41], etc.. However, these KGs are usually far from complete and noisy; thus various Knowledge Graph Completion (KGC) methods have been proposed in recent years.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Relation Adversarial Network for Low Resource Knowledge Graph Completion

Zhang

Deng

Sun

et al. 2020

Proceedings of the Web Conference 2020

Self Cite

View full text Add to dashboard Cite

Knowledge Graph Completion (KGC) has been proposed to improve Knowledge Graphs by filling in missing connections via link prediction or relation extraction. One of the main difficulties for KGC is a low resource problem. Previous approaches assume sufficient training triples to learn versatile vectors for entities and relations, or a satisfactory number of labeled sentences to train a competent relation extraction model. However, low resource relations are very common in KGs, and those newly added relations often do not have many known samples for training. In this work, we aim at predicting new facts under a challenging setting where only limited training instances are available. We propose a general framework called Weighted Relation Adversarial Network, which utilizes an adversarial procedure to help adapt knowledge/features learned from high resource relations to different but related low resource relations. Specifically, the framework takes advantage of a relation discriminator to distinguish between samples from different relations, and help learn relation-invariant features more transferable from source relations to target relations. Experimental results show that the proposed approach outperforms previous methods regarding low resource settings for both link prediction and relation extraction.

show abstract

“…KGs have been used to improve NLP performance in a wide variety of genres, including summarization or information extraction from EHRs and answering medical questions (17,28,29,33,42,62,63). KG-derived embeddings used alone, or in combination with text-derived features (48) improved performance of a variety of NLP tasks, including named-entity recognition (64), coreference resolution (65) and relation extraction (66).…”

Section: Natural Language Processing Applicationsmentioning

confidence: 99%

Knowledge-Based Biomedical Data Science

Callahan

Tripodi

Pielke-Lombardo

et al. 2020

Annu. Rev. Biomed. Data Sci.

View full text Add to dashboard Cite

Knowledge-based biomedical data science (KBDS) involves the design and implementation of computer systems that act as if they knew about biomedicine. Such systems depend on formally represented knowledge in computer systems, often in the form of knowledge graphs. Here we survey the progress in the last year in systems that use formally represented knowledge to address data science problems in both clinical and biological domains, as well as on approaches for creating knowledge graphs. Major themes include the relationships between knowledge graphs and machine learning, the use of natural language processing, and the expansion of knowledge-based approaches to novel domains, such as Chinese Traditional Medicine and biodiversity.TBoxes (for terminology), and assertions composed of them are ABoxes (for assertion) (12). Knowledge-base vs. Knowledge GraphKnowledge-bases that can be represented as graphs are often called knowledge graphs.While not all knowledge-bases are implemented as graphs (e.g. some are databases where table structure makes implicit assertions), in recent years, it has become very common to represent knowledge-bases using the Semantic Web standard or, at least be able to produce and consume Semantic Web compatible versions. For that reason, the terms knowledge-base and knowledge graph are often used interchangeably. In 2012, Google announced its proprietary Knowledge Graph, which also popularized the use of the term (13). The literature sometimes contains terminological imprecision about what the differences are between knowledge-bases, knowledge graphs and ontologies; there is a review and analysis of various published definitions (14). In this review, we use the term knowledge graph (or KG) and say a KG is grounded in the set of primitives from which it is constructed. Some KGs also include a set of logical rules that relate assertions to each other (e.g. Human TP53 is the subclass of TP53 proteins that is found in the organism human) called axioms. Biomedical ApplicationsKBDS does computation over KGs (and perhaps other inputs) to make inferences about biomedicine. While each of the publications surveyed below addresses different problems using different techniques, there are some common themes in the computational approaches to using KGs.

show abstract

Long-tail Relation Extraction via Knowledge Graph Embeddings and Graph Convolution Networks

Cited by 200 publications

References 38 publications

Open Knowledge Enrichment for Long-tail Entities

Open Knowledge Enrichment for Long-tail Entities

Relation Adversarial Network for Low Resource Knowledge Graph Completion

Knowledge-Based Biomedical Data Science

Contact Info

Product

Resources

About