Text Document Clustering: Wordnet vs. TF-IDF vs. Word Embeddings

2021-01-01 · EACL (GWC) 2021 1 · Michał Marcińczuk, Mateusz Gniewkowski, Tomasz Walkowiak, Marcin Będkowski

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, i.e., TF-IDF and wordnet-based. The experiments are conducted on three datasets containing qualification descriptions. The experiments’ results showed that wordnet-based similarity measures could compete and even outperform modern embedding-based approaches.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

ClusteringLanguage ModelingLanguage ModellingWord Embeddings

Extending and Improving Wordnet via Unsupervised Word Embeddings

2017-04-29 · Mikhail Khodak, Andrej Risteski, Christiane Fellbaum, Sanjeev Arora

This work presents an unsupervised approach for improving WordNet that builds upon recent advances in document and sense representation via distributional semantics. We apply our methods to construct Wordnets in French a…

Clustering Word Embeddings

Cluster Labeling by Word Embeddings and WordNet's Hypernymy

2018-12-01 · ALTA 2018 12 · Hanieh Poostchi, Massimo Piccardi

Cluster labeling is the assignment of representative labels to clusters obtained from the organization of a document collection. Once assigned, the labels can play an important role in applications such as navigation, se…

Clustering Descriptive Document Classification Learning Word Embeddings+1

Bilingual Embeddings with Random Walks over Multilingual Wordnets

2018-04-23 · J. Goikoetxea, A. Soroa, E. Agirre

Bilingual word embeddings represent words of two languages in the same space, and allow to transfer knowledge from one language to the other without machine translation. The main approach is to train monolingual embeddin…

Machine Translation Word Embeddings Word Similarity

ReferenceNet: a semantic-pragmatic network for capturing reference relations.

2018-01-01 · GWC 2018 1 · Piek Vossen, Filip Ilievski, Marten Postrma

In this paper, we present ReferenceNet: a semantic-pragmatic network of reference relations between synsets. Synonyms are assumed to be exchangeable in similar contexts and also word embeddings are based on sharing of lo…

Word Embeddings

Assessing Wordnets with WordNet Embeddings

2019-07-01 · GWC 2019 7 · Ruben Branco, João Rodrigues, Chakaveh Saedi, António Branco

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…