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

Shen, Jiaming; Shen, Zhihong; Xiong, Chenyan; Wang, Chi; Wang, Kuansan

doi:10.1145/3366423.3380132

Cited by 50 publications

(82 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…GenTaxo++ can use any extraction-based method [16, 22-24, 31, 36, 39, 40] as the main framework and iteratively expand the set of new concepts using concept generation (i.e., GenTaxo) to continuously improve the taxonomy completeness. We choose TaxoExpan as the extraction-based method GenTaxo++ [24]. The details of GenTaxo++ are as follows.…”

Section: Gentaxo++: Enhancing Extraction-based Methods With Gentaxomentioning

confidence: 99%

“…To this end, many recent studies aim to automatically expand or complete an existing taxonomy. For example, given a new concept, Shen et al measured the likelihood of each existing concept in the taxonomy being its hypernym and then added it as a new leaf node [24]. Manzoor et al extended the measurement to be taxonomic relatedness with implicit relational semantics [16].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Enhancing Taxonomy Completion with Concept Generation via Fusing Relational Representations

Zeng

Lin

et al. 2021

Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery &Amp; Data Mining

View full text Add to dashboard Cite

Automatic construction of a taxonomy supports many applications in e-commerce, web search, and question answering. Existing taxonomy expansion or completion methods assume that new concepts have been accurately extracted and their embedding vectors learned from the text corpus. However, one critical and fundamental challenge in fixing the incompleteness of taxonomies is the incompleteness of the extracted concepts, especially for those whose names have multiple words and consequently low frequency in the corpus. To resolve the limitations of extraction-based methods, we propose GenTaxo to enhance taxonomy completion by identifying positions in existing taxonomies that need new concepts and then generating appropriate concept names. Instead of relying on the corpus for concept embeddings, GenTaxo learns the contextual embeddings from their surrounding graph-based and language-based relational information, and leverages the corpus for pre-training a concept name generator. Experimental results demonstrate that GenTaxo improves the completeness of taxonomies over existing methods.

show abstract

Section: Gentaxo++: Enhancing Extraction-based Methods With Gentaxomentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Enhancing Taxonomy Completion with Concept Generation via Fusing Relational Representations

Zeng

Lin

et al. 2021

Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery &Amp; Data Mining

View full text Add to dashboard Cite

show abstract

“…Class Encoder. For class encoder g class (•), we follow (Shen et al, 2020) and use a graph neural network (GNN) (Kipf and Welling, 2017) to model the class taxonomy structure. This taxonomyenhanced class encoder can capture both the textual information from class surface names and structural information from the class taxonomy.…”

Section: Text Classifier Architecturementioning

confidence: 99%

TaxoClass: Hierarchical Multi-Label Text Classification Using Only Class Names

Shen

Qiu²,

et al. 2021

Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua

Self Cite

View full text Add to dashboard Cite

Hierarchical multi-label text classification (HMTC) aims to tag each document with a set of classes from a class hierarchy. Most existing HMTC methods train classifiers using massive human-labeled documents, which are often too costly to obtain in real-world applications. In this paper, we explore to conduct HMTC based on only class surface names as supervision signals. We observe that to perform HMTC, human experts typically first pinpoint a few most essential classes for the document as its "core classes", and then check core classes' ancestor classes to ensure the coverage. To mimic human experts, we propose a novel HMTC framework, named TaxoClass. Specifically, TaxoClass (1) calculates document-class similarities using a textual entailment model, (2) identifies a document's core classes and utilizes confident core classes to train a taxonomyenhanced classifier, and (3) generalizes the classifier via multi-label self-training. Our experiments on two challenging datasets show TaxoClass can achieve around 0.71 Example-F1 using only class names, outperforming the best previous method by 25%.

show abstract

“…CRIM [32] combines projection learning, trying to achieve a linear transformation which goes from hyponyms to hypernyms, with pattern-based extraction. It is also worth mentioning that recognising hypernymy represents a fundamental feature in taxonomy induction and enrichment [18,[33][34][35]. When evaluating our approach we compare ourselves with all the systems who took part in SemEval 2018 Hypernym Discovery task.…”

Section: Related Workmentioning

confidence: 99%

Fully-Unsupervised Embeddings-Based Hypernym Discovery

Atzori

Balloccu

2020

Information

View full text Add to dashboard Cite

The hypernymy relation is the one occurring between an instance term and its general term (e.g., “lion” and “animal”, “Italy” and “country”). This paper we addresses Hypernym Discovery, the NLP task that aims at finding valid hypernyms from words in a given text, proposing HyperRank, an unsupervised approach that therefore does not require manually-labeled training sets as most approaches in the literature. The proposed algorithm exploits the cosine distance of points in the vector space of word embeddings, as already proposed by previous state of the art approaches, but the ranking is then corrected by also weighting word frequencies and the absolute level of similarity, which is expected to be similar when measuring co-hyponyms and their common hypernym. This brings us two major advantages over other approaches—(1) we correct the inadequacy of semantic similarity which is known to cause a significant performance drop and (2) we take into accounts multiple words if provided, allowing to find common hypernyms for a set of co-hyponyms—a task ignored in other systems but very useful when coupled with set expansion (that finds co-hyponyms automatically). We then evaluate HyperRank against the SemEval 2018 Hypernym Discovery task and show that, regardless of the language or domain, our algorithm significantly outperforms all the existing unsupervised algorithms and some supervised ones as well. We also evaluate the algorithm on a new dataset to measure the improvements when finding hypernyms for sets of words instead of singletons.

show abstract

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

Cited by 50 publications

References 39 publications

Enhancing Taxonomy Completion with Concept Generation via Fusing Relational Representations

Enhancing Taxonomy Completion with Concept Generation via Fusing Relational Representations

TaxoClass: Hierarchical Multi-Label Text Classification Using Only Class Names

Fully-Unsupervised Embeddings-Based Hypernym Discovery

Contact Info

Product

Resources

About