中文
相关论文

相关论文: Gromov-Wasserstein Alignment of Word Embedding Spa…

200 篇论文

Cross-domain alignment between two sets of entities (e.g., objects in an image, words in a sentence) is fundamental to both computer vision and natural language processing. Existing methods mainly focus on designing advanced attention…

计算与语言 · 计算机科学 2020-07-28 Liqun Chen , Zhe Gan , Yu Cheng , Linjie Li , Lawrence Carin , Jingjing Liu

The Gromov-Wasserstein (GW) distance is an effective measure of alignment between distributions supported on distinct ambient spaces. Calculating essentially the mutual departure from isometry, it has found vast usage in domain translation…

机器学习 · 统计学 2024-12-23 Anish Chakrabarty , Arkaprabha Basu , Swagatam Das

Word embeddings are high dimensional vector representations of words that capture their semantic similarity in the vector space. There exist several algorithms for learning such embeddings both for a single language as well as for several…

计算与语言 · 计算机科学 2019-11-12 Georgios Balikas , Ioannis Partalas

A novel Gromov-Wasserstein learning framework is proposed to jointly match (align) graphs and learn embedding vectors for the associated graph nodes. Using Gromov-Wasserstein discrepancy, we measure the dissimilarity between two graphs and…

机器学习 · 计算机科学 2019-05-08 Hongteng Xu , Dixin Luo , Hongyuan Zha , Lawrence Carin

We present a versatile adaptation of existing dimensionality reduction (DR) objectives, enabling the simultaneous reduction of both sample and feature sizes. Correspondances between input and embedding samples are computed through a…

机器学习 · 计算机科学 2023-10-06 Hugues Van Assel , Cédric Vincent-Cuaz , Titouan Vayer , Rémi Flamary , Nicolas Courty

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…

计算与语言 · 计算机科学 2023-11-03 Hiroaki Yamagiwa , Sho Yokoi , Hidetoshi Shimodaira

Transferring linguistic knowledge from a pretrained language model (PLM) to acoustic feature learning has proven effective in enhancing end-to-end automatic speech recognition (E2E-ASR). However, aligning representations between linguistic…

音频与语音处理 · 电气工程与系统科学 2025-05-20 Xugang Lu , Peng Shen , Yu Tsao , Hisashi Kawai

Optimal Transport is a theory that allows to define geometrical notions of distance between probability distributions and to find correspondences, relationships, between sets of points. Many machine learning applications are derived from…

机器学习 · 统计学 2020-11-10 Titouan Vayer

We propose a novel approach for comparing distributions whose supports do not necessarily lie on the same metric space. Unlike Gromov-Wasserstein (GW) distance which compares pairwise distances of elements from each distribution, we…

机器学习 · 统计学 2021-04-23 Mokhtar Z. Alaya , Maxime Bérar , Gilles Gasso , Alain Rakotomamonjy

Recent studies have proposed different methods to improve multilingual word representations in contextualized settings including techniques that align between source and target embedding spaces. For contextualized embeddings, alignment…

计算与语言 · 计算机科学 2026-03-20 Sawsan Alqahtani , Garima Lalwani , Yi Zhang , Salvatore Romeo , Saab Mansour

Gromov-Wasserstein distance has found many applications in machine learning due to its ability to compare measures across metric spaces and its invariance to isometric transformations. However, in certain applications, this invariance…

机器学习 · 计算机科学 2023-07-20 Pinar Demetci , Quang Huy Tran , Ievgen Redko , Ritambhara Singh

Many problems in machine learning involve calculating correspondences between sets of objects, such as point clouds or images. Discrete optimal transport provides a natural and successful approach to such tasks whenever the two sets of…

机器学习 · 统计学 2019-02-28 David Alvarez-Melis , Stefanie Jegelka , Tommi S. Jaakkola

Cross-domain alignment play a key roles in tasks ranging from machine translation to transfer learning. Recently, purely unsupervised methods operating on monolingual embeddings have successfully been used to infer a bilingual lexicon…

计算与语言 · 计算机科学 2022-09-22 Aissatou Diallo , Johannes Fürnkranz

The ability to align points across two related yet incomparable point clouds (e.g. living in different spaces) plays an important role in machine learning. The Gromov-Wasserstein (GW) framework provides an increasingly popular answer to…

机器学习 · 计算机科学 2023-02-07 Meyer Scetbon , Gabriel Peyré , Marco Cuturi

We propose a new approach for unsupervised alignment of heterogeneous datasets, which maps data from two different domains without any known correspondences to a common metric space. Our method is based on an unbalanced optimal transport…

机器学习 · 计算机科学 2025-05-14 Florian Beier , Moritz Piening , Robert Beinert , Gabriele Steidl

Cross-lingual transfer of word embeddings aims to establish the semantic mappings among words in different languages by learning the transformation functions over the corresponding word embedding spaces. Successfully solving this problem…

计算与语言 · 计算机科学 2018-09-12 Ruochen Xu , Yiming Yang , Naoki Otani , Yuexin Wu

Comparing structured objects such as graphs is a fundamental operation involved in many learning tasks. To this end, the Gromov-Wasserstein (GW) distance, based on Optimal Transport (OT), has proven to be successful in handling the specific…

机器学习 · 计算机科学 2022-03-02 Cédric Vincent-Cuaz , Rémi Flamary , Marco Corneli , Titouan Vayer , Nicolas Courty

The assignment problem, a cornerstone of operations research, seeks an optimal one-to-one mapping between agents and tasks to minimize total cost. This work traces its evolution from classical formulations and algorithms to modern optimal…

最优化与控制 · 数学 2025-09-05 Iman Seyedi , Antonio Candelieri , Enza Messina , Francesco Archetti

Optimal transport (OT) and Gromov-Wasserstein (GW) alignment provide interpretable geometric frameworks for comparing, transforming, and aggregating heterogeneous datasets -- tasks ubiquitous in data science and machine learning. Because…

We consider the task of aligning two sets of points in high dimension, which has many applications in natural language processing and computer vision. As an example, it was recently shown that it is possible to infer a bilingual lexicon,…

机器学习 · 计算机科学 2018-05-30 Edouard Grave , Armand Joulin , Quentin Berthet
‹ 上一页 1 2 3 10 下一页 ›