Learning Graph Embeddings from WordNet-based Similarity Measures

Kutuzov, Andrey; Dorgham, Mohammad; Oliynyk, Oleksiy; Biemann, Chris; Panchenko, Alexander

doi:10.18653/v1/s19-1014

Cited by 9 publications

(6 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They evaluated several possibilities to combine such vectors with ordinary word embeddings obtained from large corpora like averaging or concatenating them. Another embeddings extraction method for WordNet synsets is proposed by Kutuzov et al [7]. They obtained superior results to random walks by obtaining the embedding vectors as a result of an optimization problem that ensures local (graph neighbor) and global (user annotations) consistency.…”

Section: Related Workmentioning

confidence: 99%

Spectral Text Similarity Measures

Brück

Pouly

2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Due to their ease of use and high accuracy, Word2Vec (W2V) word embeddings enjoy great success in the semantic representation of words, sentences, and whole documents as well as for semantic similarity estimation. However, they have the shortcoming that they are directly extracted from a surface representation, which does not adequately represent human thought processes and also performs poorly for highly ambiguous words. Therefore, we propose Semantic Concept Embeddings (CE) based on the MultiNet Semantic Network (SN) formalism, which addresses both shortcomings. The evaluation on a marketing target group distribution task showed that the accuracy of predicted target groups can be increased by combining traditional word embeddings with semantic CEs.

show abstract

Section: Related Workmentioning

confidence: 99%

Spectral Text Similarity Measures

Brück

Pouly

2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…Their similarities should be zero. If the counted word types are the same, the similarity calculation will be continued using WordNet [17,18]. We use WuPalmer [19,20] to search for similarities on WordNet.…”

Section: Semantic Similaritymentioning

confidence: 99%

A Different Approach on Automated Use Case Diagram Semantic Assessment

Fauzan¹,

Siahaan²,

Rochimah³

et al. 2021

IJIES

View full text Add to dashboard Cite

The use case diagram is one of the diagrams commonly taught in colleges of computer science. Assessment of use case diagrams is often an obstacle for a teacher in the learning process. It is due to the interpersonal and intrapersonal problems of the teacher in assessing. Interpersonal problems are caused by the absence of an assessment standard among teachers. Intrapersonal problems are caused by the inconsistency of a teacher in assessing many diagrams of student answers. This research aims to create a semantic use case diagram automatic assessment method. Semantic assessment is divided into two kinds, namely property and relationship. All information used is a label translated from the XMI document. Similarity assessment between labels used cosine similarity, employing WuPalmer to perform WordNet searches. The results showed that the proposed method had a substantial agreement with the teacher as an expert; however, a teacher tends to look at property information rather than relationship information to assess use case diagrams.

show abstract

“…They evaluated on the SemEval-2013 and SemEval-2015 dataset and the results indicated their method performed better than the state-of-art method in the SemEval-2013 dataset. Kutuzov [39] presented Path2vec which encoded synset paths between graph nodes into dense vectors. Their results were better than graph embedding baselines.…”

Section: Related Workmentioning

confidence: 99%

Unsupervised Predominant Sense Detection and Its Application to Text Classification

2020

View full text Add to dashboard Cite

This paper focuses on the domain-specific senses of words and proposes a method for detecting predominant sense depending on each domain. Our Domain-Specific Senses (DSS) model is an unsupervised manner and detects predominant senses in each domain. We apply a simple Markov Random Walk (MRW) model to ranking senses for each domain. It decides the importance of a sense within a graph by using the similarity of senses. The similarity of senses is obtained by using distributional representations of words from gloss texts in the thesaurus. It can capture large semantic context and thus does not require manual annotation of sense-tagged data. We used the Reuters corpus and the WordNet in the experiments. We applied the results of domain-specific senses to text classification and examined how DSS affects the overall performance of the text classification task. We compared our DSS model with one of the word sense disambiguation techniques (WSD), Context2vec, and the results demonstrate our domain-specific sense approach gains 0.053 F1 improvement on average over the WSD approach.

show abstract

Learning Graph Embeddings from WordNet-based Similarity Measures

Cited by 9 publications

References 35 publications

Spectral Text Similarity Measures

Spectral Text Similarity Measures

A Different Approach on Automated Use Case Diagram Semantic Assessment

Unsupervised Predominant Sense Detection and Its Application to Text Classification

Contact Info

Product

Resources

About