paper-with-me

Papers

Visual Pivoting for (Unsupervised) Entity Alignment

2020-09-28 · Fangyu Liu, Muhao Chen, Dan Roth, Nigel Collier

This work studies the use of visual semantic representations to align entities in heterogeneous knowledge graphs (KGs). Images are natural components of many existing KGs. By combining visual knowledge with other auxiliary information, we show that the proposed new approach, EVA, creates a holistic entity representation that provides strong signals for cross-graph entity alignment. Besides, previous entity alignment methods require human labelled seed alignment, restricting availability. EVA provides a completely unsupervised solution by leveraging the visual similarity of entities to create an initial seed dictionary (visual pivots). Experiments on benchmark data sets DBP15k and DWY15k show that EVA offers state-of-the-art performance on both monolingual and cross-lingual entity alignment tasks. Furthermore, we discover that images are particularly useful to align long-tail KG entities, which inherently lack the structural contexts necessary for capturing the correspondences.

📄 PDF Abstract BibTeX arXiv:2009.13603

Code (2)

cambridgeltl/eva 공식 구현 pytorch
sayands/sgaligner pytorch

Tasks

Entity AlignmentKnowledge GraphsMulti-modal Entity Alignment

Similar Papers 제목 키워드 기반

Unsupervised Multimodal Neural Machine Translation with Pseudo Visual Pivoting

2020-05-06 · ACL 2020 6 · Po-Yao Huang, Junjie Hu, Xiaojun Chang, Alexander Hauptmann

Unsupervised machine translation (MT) has recently achieved impressive results with monolingual corpora only. However, it is still challenging to associate source-target sentences in the latent space. As people speak dif…

Machine TranslationTranslationUnsupervised Machine Translation

Scene Graph as Pivoting: Inference-time Image-free Unsupervised Multimodal Machine Translation with Visual Scene Hallucination

2023-05-20 · Hao Fei, Qian Liu, Meishan Zhang, Min Zhang 외

In this work, we investigate a more realistic unsupervised multimodal machine translation (UMMT) setup, inference-time image-free UMMT, where the model is trained with source-text image pairs, and tested with only source…

HallucinationMachine TranslationMultimodal Machine TranslationTranslation

Unsupervised Pidgin Text Generation By Pivoting English Data and Self-Training

2020-03-18 · Ernie Chang, David Ifeoluwa Adelani, Xiaoyu Shen, Vera Demberg

West African Pidgin English is a language that is significantly spoken in West Africa, consisting of at least 75 million speakers. Nevertheless, proper machine translation systems and relevant NLP datasets for pidgin Eng…

Data-to-Text GenerationMachine TranslationText GenerationTranslation

A Fused Gromov-Wasserstein Framework for Unsupervised Knowledge Graph Entity Alignment

2023-05-11 · Jianheng Tang, Kangfei Zhao, Jia Li

Entity alignment is the task of identifying corresponding entities across different knowledge graphs (KGs). Although recent embedding-based entity alignment methods have shown significant advancements, they still struggl…

Entity AlignmentKnowledge Graphs

From Alignment to Assignment: Frustratingly Simple Unsupervised Entity Alignment

2021-09-06 · EMNLP 2021 11 · Xin Mao, Wenting Wang, Yuanbin Wu, Man Lan

Cross-lingual entity alignment (EA) aims to find the equivalent entities between crosslingual KGs, which is a crucial step for integrating KGs. Recently, many GNN-based EA methods are proposed and show decent performance…

Entity Alignment