Looking for Hyponyms in Vector Space

Abstract

The task of detecting and generating hyponyms is at the core of semantic understanding of language, and has numerous practical applications. We investigate how neural network embeddings perform on this task, compared to dependency-based vector space models, and evaluate a range of similarity measures on hyponym generation. A new asymmetric similarity measure and a combination approach are described, both of which significantly improve precision. We release three new datasets of lexical vector representations trained on the BNC and our evaluation dataset for hyponym generation.

Distributed Prediction of Relations for Entities: The Easy, The Difficult, and The Impossible

“…The accessibility of semantic relations was subsequently examined in more detail. Rei and Briscoe (2014) and Melamud et al (2014) reported successful modeling of lexical relations such as hypernymy and synonymy. Köper et al (2015) considered a broader range of relationships,with mixed results.…”

SemEval-2016 Task 13: Taxonomy Extraction Evaluation (TExEval-2)

“…NUIG-UNLP The system implements a semisupervised method that finds hypernym candidates for the provided noun phrases by representing them as distributional vectors. Roughly, this method assumes that hypernyms may be induced by adding a vector offset (Mikolov et al, 2013;Rei and Briscoe, 2014) to the corresponding hyponym representation generated by GloVe over a Wikipedia dump. The vector offset is obtained as the average offset between 200 pairs of hyponym-hypernym in the same vector space selected from trial data.…”

“…More recently, the hypernym identification subtask has attracted an increased interest from the distributional semantics community (Santus et al, 2014;Rei and Briscoe, 2014;Roller et al, 2014;Yu et al, 2015), as part of a wider effort to distinguish between different semantic relations which exist between distributional similar words (Weeds et al, 2014;Levy et al, 2015). Although this is a promising direction of research, that addresses some of the limitations of pattern-based approaches, including low coverage of domain-specific terms, most participants in this shared task opted for traditional approaches for hypernym identification, with the exception of one system (Pocostales, 2016).…”

A Short Survey on Taxonomy Learning from Text Corpora: Issues, Resources and Recent Advances

“…Other asymmetric measures are introduced in a variety of research, e.g., WeedsRec (Weeds et al, 2004), BalAPInc (Kotlerman et al, 2010), ClarkeDE (Clarke, 2009), cosWeeds, invCL (Lenci and Benotto, 2012), WeightedCosine (Rei and Briscoe, 2014). Detailed summarization of distributional similarity measures can be found in an early survey on vector space semantic models (Turney and Pantel, 2010).…”