The Effectiveness of Simple Hybrid Systems for Hypernym Discovery

  title={The Effectiveness of Simple Hybrid Systems for Hypernym Discovery},
  author={William B. Held and Nizar Habash},
Hypernymy modeling has largely been separated according to two paradigms, pattern-based methods and distributional methods. However, recent works utilizing a mix of these strategies have yielded state-of-the-art results. This paper evaluates the contribution of both paradigms to hybrid success by evaluating the benefits of hybrid treatment of baseline models from each paradigm. Even with a simple methodology for each individual system, utilizing a hybrid approach establishes new state-of-the… 

Tables from this paper

Hypernym Discovery via a Recurrent Mapping Model

This work proposes a sequential style model that recurrently maps the query words to their hypernyms, starting from the most specific ones to the less specific ones, and confirms the effectiveness of this model on SemEval-2018 Task 9.


This paper describes a combined approach to hypernym detection task. The approach combines the following techniques: distribution semantics, rulebased patterns, and modern neural networks (BERT). An

Fully-Unsupervised Embeddings-Based Hypernym Discovery

This paper addresses Hypernym Discovery, the NLP task that aims at finding valid hypernyms from words in a given text, and proposes HyperRank, an unsupervised approach that therefore does not require manually-labeled training sets as most approaches in the literature.

ProsperAMnet at the FinSim Task: Detecting hypernyms of financial concepts via measuring the information stored in sparse word representations

This paper applies an approach that quantify the extent to which the individual dimensions for such word representations convey the property that some word is the hyponym of a certain top-level concept according to an external ontology.

BiRRE: Learning Bidirectional Residual Relation Embeddings for Supervised Hypernymy Detection

A representation learning framework named Bidirectional Residual Relation Embeddings (BiRRE), which models the possibility of a term being mapped to another in the embedding space by hypernymy relations, and which outperforms strong baselines over various evaluation frameworks.

Hypernymy Detection for Low-resource Languages: A Study for Hindi, Bengali, and Amharic

This work introduces four gold-standard datasets for hypernymy detection for each of the two languages, namely, Hindi and Bengali, and two gold- standard datasets for Amharic, and introduces distributional thesaurus (DT) embeddings for all three languages using three different network embedding methods for the first time.

Hypernym-LIBre: A Free Web-based Corpus for Hypernym Detection

A new web-based corpus for hypernym detection consisting of 32 GB of high quality english paragraphs along with their part-of-speech tagged and dependency parsed versions available under an open license is described.



Improving Hypernymy Detection with an Integrated Path-based and Distributional Method

An improved path-based algorithm is suggested, in which the dependency paths are encoded using a recurrent neural network, that achieves results comparable to distributional methods.

Hypernyms under Siege: Linguistically-motivated Artillery for Hypernymy Detection

Comparison to the state-of-the-art supervised methods shows that while supervised methods generally outperform the unsupervised ones, the former are sensitive to the distribution of training instances, hurting their reliability.

SemEval-2018 Task 9: Hypernym Discovery

This paper put forward this task as a complementary benchmark for modeling hypernymy, a problem which has traditionally been cast as a binary classification task, taking a pair of candidate words as input.

Distributional Hypernym Generation by Jointly Learning Clusters and Projections

A novel word embedding-basedHypernym generation model that jointly learns clusters of hyponym-hypernym relations, i.e., hypernymy, and projections from hyponym to hypernym embeddings and boosts the performance by incorporating inner product-based similarity measures and negative examples into the objectives in learning.

Learning Syntactic Patterns for Automatic Hypernym Discovery

This paper presents a new algorithm for automatically learning hypernym (is-a) relations from text, using "dependency path" features extracted from parse trees and introduces a general-purpose formalization and generalization of these patterns.

Semantic Taxonomy Induction from Heterogenous Evidence

This work proposes a novel algorithm for inducing semantic taxonomies that flexibly incorporates evidence from multiple classifiers over heterogenous relationships to optimize the entire structure of the taxonomy, using knowledge of a word's coordinate terms to help in determining its hypernyms, and vice versa.

Automatic Acquisition of Hyponyms from Large Text Corpora

A set of lexico-syntactic patterns that are easily recognizable, that occur frequently and across text genre boundaries, and that indisputably indicate the lexical relation of interest are identified.

A Large DataBase of Hypernymy Relations Extracted from the Web

A publicly available database containing more than 400 million hypernymy relations extracted from the CommonCrawl web corpus is presented, which represents a rich source of knowledge and may be useful for many researchers.

300-sparsans at SemEval-2018 Task 9: Hypernymy as interaction of sparse attributes

300-sparsians’s participation in SemEval-2018 Task 9: Hypernym Discovery is described, with a system based on sparse coding and a formal concept hierarchy obtained from word embeddings taking first place in subtasks.

Specialising Word Vectors for Lexical Entailment

LEAR specialisation achieves state-of-the-art performance in the tasks ofhypernymy directionality, hypernymy detection, and graded lexical entailment, demonstrating the effectiveness and robustness of the proposed asymmetric specialisation model.