Every Child Should Have Parents: A Taxonomy Refinement Algorithm Based on Hyperbolic Term Embeddings

Aly, Rami; Acharya, Shantanu; Ossa, Alexander; Köhn, Arne; Biemann, Chris; Panchenko, Alexander

doi:10.18653/v1/p19-1474

Cited by 37 publications

(56 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Vedula et al [48] combine multiple features, some of which are retrieved from an external Bing Search API, into a ranking model to score candidate positions in terms of their matching scores with the query concept. Aly et al [2] first learn term embeddings in a hyperbolic space and then attach each new concept to its most similar node in the existing taxonomy based on the hyperbolic embeddings. Comparing with these methods, our TaxoExpan framework has two advantages.…”

Section: Related Workmentioning

confidence: 99%

TaxoExpan: Self-supervised Taxonomy Expansion with Position-Enhanced Graph Neural Network

Shen

Xiong

et al. 2020

Proceedings of the Web Conference 2020

View full text Add to dashboard Cite

Taxonomies consist of machine-interpretable semantics and provide valuable knowledge for many web applications. For example, online retailers (e.g., Amazon and eBay) use taxonomies for product recommendation, and web search engines (e.g., Google and Bing) leverage taxonomies to enhance query understanding. Enormous efforts have been made on constructing taxonomies either manually or semi-automatically. However, with the fast-growing volume of web content, existing taxonomies will become outdated and fail to capture emerging knowledge. Therefore, in many applications, dynamic expansions of an existing taxonomy are in great demand. In this paper, we study how to expand an existing taxonomy by adding a set of new concepts. We propose a novel self-supervised framework, named TaxoExpan, which automatically generates a set of ⟨query concept, anchor concept⟩ pairs from the existing taxonomy as training data. Using such self-supervision data, TaxoExpan learns a model to predict whether a query concept is the direct hyponym of an anchor concept. We develop two innovative techniques in TaxoExpan: (1) a position-enhanced graph neural network that encodes the local structure of an anchor concept in the existing taxonomy, and (2) a noise-robust training objective that enables the learned model to be insensitive to the label noise in the self-supervision data. Extensive experiments on three large-scale datasets from different domains demonstrate both the effectiveness and the efficiency of TaxoExpan for taxonomy expansion.

show abstract

Section: Related Workmentioning

confidence: 99%

TaxoExpan: Self-supervised Taxonomy Expansion with Position-Enhanced Graph Neural Network

Shen

Xiong

et al. 2020

Proceedings of the Web Conference 2020

View full text Add to dashboard Cite

show abstract

“…Different from Euclidean embeddings, some studies explore to characterize structures in hyperbolic embedding spaces, and use the non-linear hyperbolic distance to capture the relations between objects (Nickel and Kiela, 2017;Sala et al, 2018). This technique has shown promising performance in embedding hierarchical data, e.g., co-purchase records (Vinh et al, 2018), taxonomies (Le et al, 2019;Aly et al, 2019) and organizational charts (Chen and Quirk, 2019). Further work extends hyperbolic embeddings to capture relational hierarchies of sentences (Dhingra et al, 2018), neighborhood aggregation (Chami et al, 2019; and missing triples of a KG (Kolyvakis et al, 2020;Balazevic et al, 2019).…”

Section: Related Workmentioning

confidence: 99%

Knowledge Association with Hyperbolic Knowledge Graph Embeddings

Sun

Chen

et al. 2020

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

View full text Add to dashboard Cite

Capturing associations for knowledge graphs (KGs) through entity alignment, entity type inference and other related tasks benefits NLP applications with comprehensive knowledge representations. Recent related methods built on Euclidean embeddings are challenged by the hierarchical structures and different scales of KGs. They also depend on high embedding dimensions to realize enough expressiveness. Differently, we explore with low-dimensional hyperbolic embeddings for knowledge association. We propose a hyperbolic relational graph neural network for KG embedding and capture knowledge associations with a hyperbolic transformation. Extensive experiments on entity alignment and type inference demonstrate the effectiveness and efficiency of our method.

show abstract

“…The techniques our model based on are related to research on learning representations of symbolic data in the hyperbolic space (Krioukov et al, 2010;Kiela, 2017, 2018). Since text preserves natural hierarchical structures, Dhingra et al (2018) design a framework that learns word and sentence embeddings in an unsupervised manner from text corpora, Tifrea et al (2019) propose Poincaré GloVe to learn word embeddings based on the GloVe algorithm in the hyperbolic space, Aly et al (2019) use Poincaré embeddings to improve exiting methods to domain-specific taxonomy induction, and Le et al (2019) propose a method to predict missing hypernymy relations and correct wrong extractions for Hearst patterns based on the hyperbolic entailment cones (Ganea et al, 2018).…”

Section: Related Workmentioning

confidence: 99%

Exploring Semantic Capacity of Terms

Huang¹,

Wang²,

Chang³

et al. 2020

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

View full text Add to dashboard Cite

We introduce and study semantic capacity of terms. For example, the semantic capacity of artificial intelligence is higher than that of linear regression since artificial intelligence possesses a broader meaning scope. Understanding semantic capacity of terms will help many downstream tasks in natural language processing. For this purpose, we propose a two-step model to investigate semantic capacity of terms, which takes a large text corpus as input and can evaluate semantic capacity of terms if the text corpus can provide enough cooccurrence information of terms. Extensive experiments in three fields demonstrate the effectiveness and rationality of our model compared with well-designed baselines and human-level evaluations.

show abstract

Every Child Should Have Parents: A Taxonomy Refinement Algorithm Based on Hyperbolic Term Embeddings

Cited by 37 publications

References 24 publications

TaxoExpan: Self-supervised Taxonomy Expansion with Position-Enhanced Graph Neural Network

TaxoExpan: Self-supervised Taxonomy Expansion with Position-Enhanced Graph Neural Network

Knowledge Association with Hyperbolic Knowledge Graph Embeddings

Exploring Semantic Capacity of Terms

Contact Info

Product

Resources

About