Towards One-Size-Fits-Many: Multi-Context Attention Network for Diversity of Entity Resolution Tasks
- 22 February 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 34 (12), 6018-6032
- https://doi.org/10.1109/tkde.2021.3060790
Abstract
Entity resolution (ER) identifies data instances referring to the same real-world entity and has received enormous research attention. In this paper, we examine the task of ER from a broader perspective, with its input extended from textual records, which are conventionally studied in the literature, to other modalities such as check-in sequences, GPS trajectories and surveillance video frames to generate new applications. Our goal in this paper is to design an effective model to uniformly support all these ER applications with different input formats. Technically, we fully exploit the semantic contexts of embedding vectors for the pair of input instances. In particular, we propose an integrated multi-context attention framework that takes into account self-attention, pair-attention and global-attention from three types of context. The idea can be further extended to incorporate attribute attention in order to support structured datasets. We conduct extensive experiments on a diverse class of entity resolutions tasks, including tasks on unstructured, structured and dirty textual records, check-in sequences, GPS trajectories and surveillance video frames. The experimental results verified the effectiveness and generality of our model. When compared with strong baselines in these applications, our model can achieve superior or comparative performance.Keywords
Funding Information
- National Natural Science Foundation of China (61702432, 61672455)
- Singapore Ministry of Education (T1251RES1913)
This publication has 46 references indexed in Scilit:
- Person Re-Identification with Discriminatively Trained Viewpoint Invariant DictionariesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- Effective Approaches to Attention-based Neural Machine TranslationPublished by Association for Computational Linguistics (ACL) ,2015
- Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine TranslationPublished by Association for Computational Linguistics (ACL) ,2014
- Glove: Global Vectors for Word RepresentationPublished by Association for Computational Linguistics (ACL) ,2014
- Evaluation of entity resolution approaches on real-world match problemsProceedings of the VLDB Endowment, 2010
- Adaptive name matching in information integrationIEEE Intelligent Systems, 2003
- Adaptive duplicate detection using learnable string similarity measuresPublished by Association for Computing Machinery (ACM) ,2003
- Interactive deduplication using active learningPublished by Association for Computing Machinery (ACM) ,2002
- Data integration using similarity joins and a word-based information representation languageACM Transactions on Information Systems, 2000
- Long Short-Term MemoryNeural Computation, 1997