Hearst Patterns Revisited: Automatic Hypernym Detection from Large Text Corpora

Roller, Stephen; Kiela, Douwe; Nickel, Maximilian

doi:10.18653/v1/p18-2057

Cited by 89 publications

(110 citation statements)

References 19 publications

Supporting

Mentioning

110

Contrasting

Order By: Relevance

“…To evaluate the efficacy of our method, we evaluate on several commonly-used hypernymy benchmarks (as described in (Roller et al, 2018)) as well as in a reconstruction setting (as described in (Nickel and Kiela, 2017)). Following Roller et al (2018), we compare to the following methods for unsupervised hypernymy detection:…”

Section: Methodsmentioning

confidence: 99%

“…Our own experiments, and those of Seitner et al (2016), demonstrate that this approach can be scaled to large corpora such as COM-MONCRAWL. 1 As Roller et al (2018) showed, pattern matches also provide important contextual constraints which boost signal compared to methods based on the Distributional Inclusion Hypothesis.…”

Section: Hearst Graphmentioning

confidence: 99%

“…For this purpose, we combine Hearst patterns with recently introduced hyperbolic arXiv:1902.00913v1 [cs.CL] 3 Feb 2019 embeddings Kiela, 2017, 2018), what provides important advantages for this task. First, as Roller et al (2018) showed recently, Hearst patterns provide important constraints for hypernymy extraction from distributional contexts. However, it is also well-known that Hearst patterns are prone to missing and wrong extractions, as words must co-occur in exactly the right pattern to be detected successfully.…”

Section: Introductionmentioning

confidence: 97%

See 2 more Smart Citations

Inferring Concept Hierarchies from Text Corpora via Hyperbolic Embeddings

Roller

Papaxanthos

et al. 2019

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Self Cite

View full text Add to dashboard Cite

We consider the task of inferring is-a relationships from large text corpora. For this purpose, we propose a new method combining hyperbolic embeddings and Hearst patterns. This approach allows us to set appropriate constraints for inferring concept hierarchies from distributional contexts while also being able to predict missing is-a-relationships and to correct wrong extractions. Moreover -and in contrast with other methods -the hierarchical nature of hyperbolic space allows us to learn highly efficient representations and to improve the taxonomic consistency of the inferred hierarchies. Experimentally, we show that our approach achieves state-of-the-art performance on several commonly-used benchmarks.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Hearst Graphmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 97%

See 1 more Smart Citation

Inferring Concept Hierarchies from Text Corpora via Hyperbolic Embeddings

Roller

Papaxanthos

et al. 2019

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Self Cite

View full text Add to dashboard Cite

show abstract

“…We remark that the above two approaches both yield contextual units with granularity more coarse than the Simplest, while one can also dene context granularity that is ner than the simplest. For instance, using explicit network structure, meta-graph [32], a denition of a ner contextual unit in the DBLP network can be two papers wrien by the same author. Under this denition, only two keywords simultaneously tagged to an authors' two papers are considered linked to a common contextual unit.…”

Section: Exploiting Context Granularitymentioning

confidence: 99%

“…A substantial number of methods have been proposed to extend the original six Hearst patterns [11,17,57]. It has been shown that Hearst pattern based methods tend to achieve high precision with compromised recall [22,32,53]. Attempts have also been made to further improve the recall [1,24,47].…”

Section: Case Study: Taxonomy Constructionmentioning

confidence: 99%

Discovering Hypernymy in Text-Rich Heterogeneous Information Network by Exploiting Context Granularity

Shi

Shen

et al. 2019

Proceedings of the 28th ACM International Conference on Information and Knowledge Management

View full text Add to dashboard Cite

Text-rich heterogeneous information networks (text-rich HINs) are ubiquitous in real-world applications. Hypernymy, also known as is-a relation or subclass-of relation, lays in the core of many knowledge graphs and benefits many downstream applications. Existing methods of hypernymy discovery either leverage textual patterns to extract explicitly mentioned hypernym-hyponym pairs, or learn a distributional representation for each term of interest based its context. These approaches rely on statistical signals from the textual corpus, and their effectiveness would therefore be hindered when the signals from the corpus are not sufficient for all terms of interest. In this work, we propose to discover hypernymy in text-rich HINs, which can introduce additional high-quality signals. We develop a new framework, named HyperMine, that exploits multi-granular contexts and combines signals from both text and network without human labeled data. HyperMine extends the definition of "context" to the scenario of text-rich HIN. For example, we can define typed nodes and communities as contexts. These contexts encode signals of different granularities and we feed them into a hypernymy inference model. HyperMine learns this model using weak supervision acquired based on high-precision textual patterns. Extensive experiments on two large real-world datasets demonstrate the effectiveness of HyperMine and the utility of modeling context granularity. We further show a case study that a high-quality taxonomy can be generated solely based on the hypernymy discovered by HyperMine.

show abstract

Improving taxonomic relation learning via incorporating relation descriptions into word embeddings

Huang

Luo

Huang

et al. 2020

Concurrency and Computation

View full text Add to dashboard Cite

SummaryTaxonomic relations play an important role in various Natural Language Processing (NLP) tasks (eg, information extraction, question answering and knowledge inference). Existing approaches on embedding‐based taxonomic relation learning mainly rely on the word embeddings trained using co‐occurrence‐based similarity learning. However, the performance of these approaches is not quite satisfactory due to the lack of sufficient taxonomic semantic knowledge within word embeddings. To solve this problem, we propose an improved embedding‐based approach to learn taxonomic relations via incorporating relation descriptions into word embeddings. First, to capture additional taxonomic semantic knowledge, we train special word embeddings using not only co‐occurrence information of words but also relation descriptions (eg, taxonomic seed relations and their contextual triples). Then, using the trained word embeddings as features, we employ two learning models to identify and predict taxonomic relations, namely, offset‐based classification model and offset‐based similarity model. Experimental results on four real‐world domain datasets demonstrate that our proposed approach can capture additional taxonomic semantic knowledge and reduce dependence on the training dataset, outperforming the state‐of‐the‐art compared approaches on the taxonomic relation learning task.

show abstract

Hearst Patterns Revisited: Automatic Hypernym Detection from Large Text Corpora

Cited by 89 publications

References 19 publications

Inferring Concept Hierarchies from Text Corpora via Hyperbolic Embeddings

Inferring Concept Hierarchies from Text Corpora via Hyperbolic Embeddings

Discovering Hypernymy in Text-Rich Heterogeneous Information Network by Exploiting Context Granularity

Improving taxonomic relation learning via incorporating relation descriptions into word embeddings

Contact Info

Product

Resources

About