English
Related papers

Related papers: Linear-Complexity Relaxed Word Mover's Distance wi…

200 papers

The Word Mover's Distance (WMD) proposed by Kusner et al. is a distance between documents that takes advantage of semantic relations among words that are captured by their embeddings. This distance proved to be quite effective, obtaining…

Computation and Language · Computer Science 2020-05-12 Matheus Werner , Eduardo Laber

The Word Mover's Distance (WMD) is a metric that measures the semantic dissimilarity between two text documents by computing the cost of moving all words of a source/query document to the most similar words of a target document optimally.…

Machine Learning · Computer Science 2021-03-24 Jesmin Jahan Tithi , Fabrizio Petrini

The Word Movers Distance (WMD) measures the semantic dissimilarity between two text documents by computing the cost of optimally moving all words of a source/query document to the most similar words of a target document. Computing WMD…

Distributed, Parallel, and Cluster Computing · Computer Science 2022-04-27 Jesmin Jahan Tithi , Fabrizio Petrini

While the celebrated Word2Vec technique yields semantically rich representations for individual words, there has been relatively less success in extending to generate unsupervised sentences or documents embeddings. Recent work has…

Computation and Language · Computer Science 2018-11-06 Lingfei Wu , Ian E. H. Yen , Kun Xu , Fangli Xu , Avinash Balakrishnan , Pin-Yu Chen , Pradeep Ravikumar , Michael J. Witbrock

As a fundamental problem of natural language processing, it is important to measure the distance between different documents. Among the existing methods, the Word Mover's Distance (WMD) has shown remarkable success in document semantic…

Machine Learning · Computer Science 2019-07-12 Zihao Wang , Datong Zhou , Yong Zhang , Hao Wu , Chenglong Bao

Measuring the semantic similarity between two sentences is still an important task. The word mover's distance (WMD) computes the similarity via the optimal alignment between the sets of word embeddings. However, WMD does not utilize word…

Computation and Language · Computer Science 2023-11-03 Hiroaki Yamagiwa , Sho Yokoi , Hidetoshi Shimodaira

The surge in scientific publications challenges the use of publication counts as a measure of scientific progress, requiring alternative metrics that emphasize the quality and novelty of scientific contributions rather than sheer quantity.…

Digital Libraries · Computer Science 2024-09-04 Luca D'Aniello , Nicolas Robinson-Garcia , Massimo Aria , Corrado Cuccurullo

The Earth Mover's Distance (EMD) is a state-of-the art metric for comparing discrete probability distributions, but its high distinguishability comes at a high cost in computational complexity. Even though linear-complexity approximation…

Machine Learning · Computer Science 2019-05-29 Kubilay Atasu , Thomas Mittelholzer

Word Mover's Distance (WMD) computes the distance between words and models text similarity with the moving cost between words in two text sequences. Yet, it does not offer good performance in sentence similarity evaluation since it does not…

Computation and Language · Computer Science 2022-06-22 Chengwei Wei , Bin Wang , C. -C. Jay Kuo

Assessing the proper difficulty levels of reading materials or texts in general is the first step towards effective comprehension and learning. In this study, we improve the conventional methodology of automatic readability assessment by…

Computation and Language · Computer Science 2021-09-21 Joseph Marvin Imperial , Ethel Ong

The word mover's distance (WMD) is a fundamental technique for measuring the similarity of two documents. As the crux of WMD, it can take advantage of the underlying geometry of the word space by employing an optimal transport formulation.…

Machine Learning · Computer Science 2022-06-16 Ryoma Sato , Makoto Yamada , Hisashi Kashima

The word mover's distance (WMD) is a popular semantic similarity metric for two texts. This position paper studies several possible extensions of WMD. We experiment with the frequency of words in the corpus as a weighting factor and the…

Computation and Language · Computer Science 2022-02-09 Ilya Smirnov , Ivan P. Yamshchikov

Despite the increasing popularity of NLP in the humanities and social sciences, advances in model performance and complexity have been accompanied by concerns about interpretability and explanatory power for sociocultural analysis. One…

Computation and Language · Computer Science 2021-10-15 Mikael Brunila , Jack LaViolette

Search behaviour is characterised using synonymy and polysemy as users often want to search information based on meaning. Semantic representation strategies represent a move towards richer associative connections that can adequately capture…

Information Retrieval · Computer Science 2026-02-06 Niall McCarroll , Kevin Curran , Eugene McNamee , Angela Clist , Andrew Brammer

Many information retrieval algorithms rely on the notion of a good distance that allows to efficiently compare objects of different nature. Recently, a new promising metric called Word Mover's Distance was proposed to measure the divergence…

Computation and Language · Computer Science 2018-05-14 Georgios Balikas , Charlotte Laclau , Ievgen Redko , Massih-Reza Amini

Since the seminal work of Mikolov et al., word embeddings have become the preferred word representations for many natural language processing tasks. Document similarity measures extracted from word embeddings, such as the soft cosine…

Information Retrieval · Computer Science 2020-04-02 Vít Novotný , Eniafe Festus Ayetiran , Michal Štefánik , Petr Sojka

Prior work inspired by compression algorithms has described how the Burrows Wheeler Transform can be used to create a distance measure for bioinformatics problems. We describe issues with this approach that were not widely known, and…

Cryptography and Security · Computer Science 2020-02-19 Edward Raff , Charles Nicholas , Mark McLean

The main approach of traditional information retrieval (IR) is to examine how many words from a query appear in a document. A drawback of this approach, however, is that it may fail to detect relevant documents where no or only few words…

Computation and Language · Computer Science 2017-10-19 Sun Kim , Nicolas Fiorini , W. John Wilbur , Zhiyong Lu

Generalized Benders decomposition (GBD) is a globally optimal algorithm for mixed integer nonlinear programming (MINLP) problems, which are NP-hard and can be widely found in the area of wireless resource allocation. The main idea of GBD is…

Information Theory · Computer Science 2020-10-16 Mengyuan Lee , Ning Ma , Guanding Yu , Huaiyu Dai

It is well-understood that different algorithms, training processes, and corpora produce different word embeddings. However, less is known about the relation between different embedding spaces, i.e. how far different sets of embeddings…

Computation and Language · Computer Science 2020-05-19 Xuhui Zhou , Zaixiang Zheng , Shujian Huang
‹ Prev 1 2 3 10 Next ›