Ontology Completion Using Graph Convolutional Networks

Li, Na; Bouraoui, Zied; Schockaert, Steven

doi:10.1007/978-3-030-30793-6_25

Cited by 14 publications

(17 citation statements)

References 94 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There exist numerous approaches to knowledge base completion, which make use of various neural network architectures described in review papers [55,61]. Most of them apply low-dimensional graph embeddings [13,72], deep learning architectures like autoencoders [86] or graph convolutional networks [23,41,70]. Another group of approaches makes use of tensor decomposition approaches: Tucker decomposition [3] and Canonical Polyadic decomposition (CANDECOMP/PARAFAC) [39,40].…”

Section: Related Workmentioning

confidence: 99%

Taxonomy enrichment with text and graph vector representations

Nikishina

Tikhomirov

Logacheva

et al. 2022

View full text Add to dashboard Cite

Knowledge graphs such as DBpedia, Freebase or Wikidata always contain a taxonomic backbone that allows the arrangement and structuring of various concepts in accordance with hypo-hypernym (“class-subclass”) relationship. With the rapid growth of lexical resources for specific domains, the problem of automatic extension of the existing knowledge bases with new words is becoming more and more widespread. In this paper, we address the problem of taxonomy enrichment which aims at adding new words to the existing taxonomy. We present a new method which allows achieving high results on this task with little effort. It uses the resources which exist for the majority of languages, making the method universal. We extend our method by incorporating deep representations of graph structures like node2vec, Poincaré embeddings, GCN etc. that have recently demonstrated promising results on various NLP tasks. Furthermore, combining these representations with word embeddings allows us to beat the state of the art. We conduct a comprehensive study of the existing approaches to taxonomy enrichment based on word and graph vector representations and their fusion approaches. We also explore the ways of using deep learning architectures to extend taxonomic backbones of knowledge graphs. We create a number of datasets for taxonomy extension for English and Russian. We achieve state-of-the-art results across different datasets and provide an in-depth error analysis of mistakes.

show abstract

Section: Related Workmentioning

confidence: 99%

Taxonomy enrichment with text and graph vector representations

Nikishina

Tikhomirov

Logacheva

et al. 2022

View full text Add to dashboard Cite

show abstract

“…There exist numerous approaches to knowledge base completion, which make use of various neural network architectures described in review papers [13,14]. Most of them apply low-dimensional graph embeddings [15,16], deep learning architectures like autoencoders [17] or graph convolutional networks [18][19][20]. Another group of approaches makes use of tensor decomposition approaches: Tucker decomposition [21] and Canonical Polyadic decomposition (CAN-DECOMP/PARAFAC) [22,23].…”

Section: Related Workmentioning

confidence: 99%

Taxonomy Enrichment with Text and Graph Vector Representations

Nikishina¹,

Tikhomirov²,

Logacheva³

et al. 2022

Preprint

View full text Add to dashboard Cite

Knowledge graphs such as DBpedia, Freebase or Wikidata always contain a taxonomic backbone that allows the arrangement and structuring of various concepts in accordance with hypo-hypernym ("class-subclass") relationship. With the rapid growth of lexical resources for specific domains, the problem of automatic extension of the existing knowledge bases with new words is becoming more and more widespread. In this paper, we address the problem of taxonomy enrichment which aims at adding new words to the existing taxonomy.We present a new method which allows achieving high results on this task with little effort. It uses the resources which exist for the majority of languages, making the method universal. We extend our method by incorporating deep representations of graph structures like node2vec, Poincaré embeddings, GCN etc. that have recently demonstrated promising results on various NLP tasks. Furthermore, combining these representations with word embeddings allows us to beat the state of the art.We conduct a comprehensive study of the existing approaches to taxonomy enrichment based on word and graph vector representations and their fusion approaches. We also explore the ways of using deep learning architectures to extend taxonomic backbones of knowledge graphs. We create a number of datasets for taxonomy extension for English and Russian. We achieve state-of-the-art results across different datasets and provide an in-depth error analysis of mistakes.

show abstract

“…However, static word vectors remain important in applications where word meaning has to be modelled in the absence of (sentence) context. For instance, static word vectors are needed for zero-shot image classification (Socher et al, 2013) and zero-shot entity typing (Ma et al, 2016), for ontology alignment (Kolyvakis et al, 2018) and completion (Li et al, 2019), taxonomy learning (Bordea et al, 2015(Bordea et al, , 2016, or for representing query terms in information retrieval systems (Nikolaev and Kotov, 2020). Moreover, Liu et al (2020) recently found that static word vectors can complement CLMs, by serving as anchors for contextualized vectors, while Alghanmi et al (2020) found that incorporating static word vectors could improve the performance of BERT for social media classification.…”

Section: Introductionmentioning

confidence: 99%

Deriving Word Vectors from Contextualized Language Models using Topic-Aware Mention Selection

Wang¹,

Bouraoui²,

Espinosa-Anke³

et al. 2021

Proceedings of the 6th Workshop on Representation Learning for NLP (RepL4NLP-2021)

Self Cite

View full text Add to dashboard Cite

One of the long-standing challenges in lexical semantics consists in learning representations of words which reflect their semantic properties. The remarkable success of word embeddings for this purpose suggests that highquality representations can be obtained by summarizing the sentence contexts of word mentions. In this paper, we propose a method for learning word representations that follows this basic strategy, but differs from standard word embeddings in two important ways. First, we take advantage of contextualized language models (CLMs) rather than bags of word vectors to encode contexts. Second, rather than learning a word vector directly, we use a topic model to partition the contexts in which words appear, and then learn different topic-specific vectors for each word. Finally, we use a taskspecific supervision signal to make a soft selection of the resulting vectors. We show that this simple strategy leads to high-quality word vectors, which are more predictive of semantic properties than word embeddings and existing CLM-based strategies.

show abstract

Ontology Completion Using Graph Convolutional Networks

Cited by 14 publications

References 94 publications

Taxonomy enrichment with text and graph vector representations

Taxonomy enrichment with text and graph vector representations

Taxonomy Enrichment with Text and Graph Vector Representations

Deriving Word Vectors from Contextualized Language Models using Topic-Aware Mention Selection

Contact Info

Product

Resources

About