The Effectiveness of Simple Hybrid Systems for Hypernym Discovery

@inproceedings{Held2019TheEO,
  title={The Effectiveness of Simple Hybrid Systems for Hypernym Discovery},
  author={William B. Held and Nizar Habash},
  booktitle={ACL},
  year={2019}
}
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… Expand
Hypernym Discovery via a Recurrent Mapping Model
TLDR
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. Expand
COMBINED APPROACH TO HYPERNYM DETECTION FOR THESAURUS ENRICHMENT
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). AnExpand
Fully-Unsupervised Embeddings-Based Hypernym Discovery
TLDR
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. Expand
ProsperAMnet at the FinSim Task: Detecting hypernyms of financial concepts via measuring the information stored in sparse word representations
In this paper we propose and carefully evaluate the application of an information theoretic approach for the detection of hypernyms for financial concepts. Our algorithm is based on the applicationExpand
BiRRE: Learning Bidirectional Residual Relation Embeddings for Supervised Hypernymy Detection
TLDR
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. Expand
Hypernym-LIBre: A Free Web-based Corpus for Hypernym Detection
TLDR
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. Expand

References

SHOWING 1-10 OF 20 REFERENCES
Why we have switched from building full-fledged taxonomies to simply detecting hypernymy relations
TLDR
This paper analyzes issues related to current evaluation procedures of taxonomy learning approaches, and proposes three potential avenues for future work so that is-a relations and resources based on them play a more important role in downstream NLP applications. Expand
Improving Hypernymy Detection with an Integrated Path-based and Distributional Method
TLDR
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. Expand
Hypernyms under Siege: Linguistically-motivated Artillery for Hypernymy Detection
TLDR
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. Expand
SemEval-2018 Task 9: Hypernym Discovery
TLDR
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. Expand
Hearst Patterns Revisited: Automatic Hypernym Detection from Large Text Corpora
TLDR
It is found that simple pattern-based methods consistently outperform distributional methods on common benchmark datasets and shows that pattern- based models provide important contextual constraints which are not yet captured in Distributional methods. Expand
Distributional Hypernym Generation by Jointly Learning Clusters and Projections
TLDR
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. Expand
Learning Syntactic Patterns for Automatic Hypernym Discovery
TLDR
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. Expand
Semantic Taxonomy Induction from Heterogenous Evidence
TLDR
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. Expand
Automatic Acquisition of Hyponyms from Large Text Corpora
TLDR
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. Expand
A Large DataBase of Hypernymy Relations Extracted from the Web
TLDR
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. Expand
...
1
2
...