Learning Graph Embeddings from WordNet-based Similarity Measures
We present path2vec, a new approach for learning graph embeddings that relies on structural measures of pairwise node similarities. The model learns representations for nodes in a dense space that approximate a given user-defined graph distance measure, such as e.g. the shortest path distance or distance measures that take information beyond the graph structure into account. Evaluation of the proposed model on semantic similarity and word sense disambiguation tasks, using various WordNet-based similarity measures, show that our approach yields competitive results, outperforming strong graph embedding baselines. The model is computationally efficient, being orders of magnitude faster than the direct computation of graph-based distances.
Code (0)
등록된 구현이 없습니다.
Tasks
Graph EmbeddingSemantic SimilaritySemantic Textual SimilarityWord Sense DisambiguationSimilar Papers 제목 키워드 기반
Making Fast Graph-based Algorithms with Graph Metric Embeddings
The computation of distance measures between nodes in graphs is inefficient and does not scale to large graphs. We explore dense vector representations as an effective way to approximate the same information: we introduc…
Semantic SimilaritySemantic Textual SimilarityWord Sense DisambiguationWord SimilarityAssessing Wordnets with WordNet Embeddings
An effective conversion method was proposed in the literature to obtain a lexical semantic space from a lexical semantic graph, thus permitting to obtain WordNet embeddings from WordNets. In this paper, we propose the ex…
Semantic SimilaritySemantic Textual SimilarityWord EmbeddingsText Document Clustering: Wordnet vs. TF-IDF vs. Word Embeddings
In the paper, we deal with the problem of unsupervised text document clustering for the Polish language. Our goal is to compare the modern approaches based on language modeling (doc2vec and BERT) with the classical ones,…
ClusteringLanguage ModelingLanguage ModellingWord EmbeddingsDense Embeddings Preserving the Semantic Relationships in WordNet
In this paper, we provide a novel way to generate low dimensional vector embeddings for the noun and verb synsets in WordNet, where the hypernym-hyponym relationship is preserved in the embeddings. We call this embedding…
IndoWordNet::Similarity- Computing Semantic Similarity and Relatedness using IndoWordNet
Semantic similarity and relatedness measures play an important role in natural language processing applications. In this paper, we present the IndoWordNet::Similarity tool and interface, designed for computing the semant…
Semantic SimilaritySemantic Textual Similarity