Supervised Word Mover's Distance

By Gao Huang, Chuan Guo, Matt J. Kusner, Yu Sun, Fei Sha, Kilian Q. Weinberger. 2016

195 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Learning protein sequence embeddings using information from structure (2019, background): “Word Mover’s Distance [27], in which documents are compared based on an alignment between their words using pretrained word vectors, and it’s supervised variant [28], in which word vector’s are linearly transformed given document class supervision, are also related.”
Learning Generative Models with Sinkhorn Divergences (2017, methodology): “The benefits of this regularization has opened the path to many applications of the Wasserstein distance in relevant learning problems [8, 13, 18, 28].”
Message Passing Attention Networks for Document Understanding (2019, methodology): “S-WMD (Huang et al., 2016) is a supervised extension of the Word Mover’s Distance.”
Optimal Transport for structured data with application on graphs (2018, background): “(Huang et al., 2016; Courty et al., 2017; Arjovsky et al., 2017)) because of its capacity to compare empirical distributions, and also the recent advances in solving the underlying problem (Peyré & Cuturi, 2018).”
Sentence Mover’s Similarity: Automatic Evaluation for Multi-Sentence Texts (2019, background): “…word embeddings (Zhang et al., 2017; Wu et al., 2018), textual entailment (Sulea, 2017), document similarity and classiﬁcation (Kusner et al., 2015; Huang et al., 2016; Atasu et al., 2017), image captioning (Kil-ickaya et al., 2017), document retrieval (Balikas et al., 2018), clustering for…”
Rectify Heterogeneous Models with Semantic Mapping (2018, methodology): “For example, in image query (Rubner et al., 1998), document classification (Huang et al., 2016), domain adaptation (Perrot et al., 2016; Courty et al., 2017a;b), and barycenter discovery (Cuturi & Doucet, 2014).”
Context Mover's Distance & Barycenters: Optimal transport of contexts for building representations (2018, background): “These include document distances (Kusner et al., 2015; Huang et al., 2016), topic modelling (Rolet et al.”
Thermodynamic Unification of Optimal Transport: Thermodynamic Uncertainty Relation, Minimum Dissipation, and Thermodynamic Speed Limits (2022, background): “Currently, this problem has several theoretical and practical applications in a variety of scientific fields, including statistics and machine learning [70], computer vision [71], linguistics [72], classical mechanics [73], and molecular biology [74].”
Earth Mover’s Distance Minimization for Unsupervised Bilingual Lexicon Induction (2017, methodology): “The earth mover’s distance (EMD) is a powerful tool widely used in computer vision and natural language processing (Rubner et al., 1998; Kus-ner et al., 2015; Huang et al., 2016; Zhang et al., 2016b,a).”