Sharp asymptotic and finite-sample rates of convergence of empirical measures in Wasserstein distance
Sharp asymptotic and finite-sample rates of convergence of empirical measures in Wasserstein
distance Page 1 Bernoulli 25(4A), 2019, 2620–2648 https://doi.org/10.3150/18-BEJ1065 Sharp …
distance Page 1 Bernoulli 25(4A), 2019, 2620–2648 https://doi.org/10.3150/18-BEJ1065 Sharp …
Earth mover's distance minimization for unsupervised bilingual lexicon induction
Cross-lingual natural language processing hinges on the premise that there exists
invariance across languages. At the word level, researchers have identified such invariance …
invariance across languages. At the word level, researchers have identified such invariance …
XQA: A cross-lingual open-domain question answering dataset
Open-domain question answering (OpenQA) aims to answer questions through text retrieval
and reading comprehension. Recently, lots of neural network-based models have been …
and reading comprehension. Recently, lots of neural network-based models have been …
Distances between probability distributions of different dimensions
Comparing probability distributions is an indispensable and ubiquitous task in machine
learning and statistics. The most common way to compare a pair of Borel probability …
learning and statistics. The most common way to compare a pair of Borel probability …
Minimax distribution estimation in Wasserstein distance
The Wasserstein metric is an important measure of distance between probability
distributions, with applications in machine learning, statistics, probability theory, and data …
distributions, with applications in machine learning, statistics, probability theory, and data …
Re-evaluating word mover's distance
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 …
two documents. As the crux of WMD, it can take advantage of the underlying geometry of the …
A hybrid semantic query expansion approach for Arabic information retrieval
In fact, most of information retrieval systems retrieve documents based on keywords
matching, which are certainly fail at retrieving documents that have similar meaning with …
matching, which are certainly fail at retrieving documents that have similar meaning with …
A distribution-based model to learn bilingual word embeddings
H Cao, T Zhao, S Zhang, Y Meng - Proceedings of COLING 2016 …, 2016 - aclanthology.org
We introduce a distribution based model to learn bilingual word embeddings from
monolingual data. It is simple, effective and does not require any parallel data or any seed …
monolingual data. It is simple, effective and does not require any parallel data or any seed …
Inference for projection-based wasserstein distances on finite spaces
R Okano, M Imaizumi - arXiv preprint arXiv:2202.05495, 2022 - arxiv.org
The Wasserstein distance is a distance between two probability distributions and has
recently gained increasing popularity in statistics and machine learning, owing to its …
recently gained increasing popularity in statistics and machine learning, owing to its …
How can large language models become more human?
Psycholinguistic experiments reveal that efficiency of human language use is founded on
predictions at both syntactic and lexical levels. Previous models of human prediction …
predictions at both syntactic and lexical levels. Previous models of human prediction …