Computational optimal transport: With applications to data science

G Peyré, M Cuturi - Foundations and Trends® in Machine …, 2019‏ - nowpublishers.com
Optimal transport (OT) theory can be informally described using the words of the French
mathematician Gaspard Monge (1746–1818): A worker with a shovel in hand has to move a …

Measurement of text similarity: a survey

J Wang, Y Dong - Information, 2020‏ - mdpi.com
Text similarity measurement is the basis of natural language processing tasks, which play an
important role in information retrieval, automatic question answering, machine translation …

Thermodynamic unification of optimal transport: Thermodynamic uncertainty relation, minimum dissipation, and thermodynamic speed limits

T Van Vu, K Saito - Physical Review X, 2023‏ - APS
Thermodynamics serves as a universal means for studying physical systems from an energy
perspective. In recent years, with the establishment of the field of stochastic and quantum …

Learning generative models with sinkhorn divergences

A Genevay, G Peyré, M Cuturi - International Conference on …, 2018‏ - proceedings.mlr.press
The ability to compare two degenerate probability distributions, that is two distributions
supported on low-dimensional manifolds in much higher-dimensional spaces, is a crucial …

Sample complexity of Sinkhorn divergences

A Genevay, L Chizat, F Bach… - The 22nd …, 2019‏ - proceedings.mlr.press
Optimal transport (OT) and maximum mean discrepancies (MMD) are now routinely used in
machine learning to compare probability measures. We focus in this paper on Sinkhorn …

An introduction to neural information retrieval

B Mitra, N Craswell - Foundations and Trends® in Information …, 2018‏ - nowpublishers.com
Neural ranking models for information retrieval (IR) use shallow or deep neural networks to
rank search results in response to a query. Traditional learning to rank models employ …

Low-resource languages: A review of past work and future challenges

A Magueresse, V Carles, E Heetderks - arxiv preprint arxiv:2006.07264, 2020‏ - arxiv.org
A current problem in NLP is massaging and processing low-resource languages which lack
useful training attributes such as supervised data, number of native speakers or experts, etc …

Sentence mover's similarity: Automatic evaluation for multi-sentence texts

E Clark, A Celikyilmaz, NA Smith - … of the 57th Annual Meeting of …, 2019‏ - aclanthology.org
For evaluating machine-generated texts, automatic methods hold the promise of avoiding
collection of human judgments, which can be expensive and time-consuming. The most …

Optimal transport for structured data with application on graphs

V Titouan, N Courty, R Tavenard… - … on Machine Learning, 2019‏ - proceedings.mlr.press
This work considers the problem of computing distances between structured objects such as
undirected graphs, seen as probability distributions in a specific metric space. We consider a …

Neural models for information retrieval

B Mitra, N Craswell - arxiv preprint arxiv:1705.01509, 2017‏ - arxiv.org
Neural ranking models for information retrieval (IR) use shallow or deep neural networks to
rank search results in response to a query. Traditional learning to rank models employ …