James B. Wendt
James is a Software Engineer at Google DeepMind currently focusing on improving the structural data understanding capabilities of large generative models. Previously in Google Research, he focused on topics related to low-resource information extraction, semi-supervised learning, and data management and quality. Prior work also included developing large scale privacy-safe information extraction and data management systems for private corpora. Prior to joining Google, James earned his Ph.D. at UCLA under the guidance of Miodrag Potkonjak, where he explored methods for hardware security and low power circuit and system design. You can see his full list of publications on Google Scholar and
his personal site.
Research Areas
Authored Publications
Sort By
Google
FieldSwap: Data Augmentation for Effective Form-Like Document Extraction
Seth Ebner
IEEE 40th International Conference on Data Engineering (ICDE) (2024), pp. 4722-4732
Selective Labeling: How to Radically Lower Data-Labeling Costs for Document Extraction Models
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, ACL, pp. 3847-3860
Glean: Structured Extractions from Templatic Documents
Proceedings of the VLDB Endowment (2021), pp. 997-1005
Data-Efficient Information Extraction from Form-Like Documents
Document Intelligence Workshop @ KDD 2021
Migrating a Privacy-Safe Information Extraction System to a Software 2.0 Design
Nguyen Ha Vo
Proceedings of the 10th Annual Conference on Innovative Data Systems Research (2020)
Representation Learning for Information Extraction from Form-like Documents
Bodhisattwa Majumder
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (ACL 2020), pp. 6495-6504
RiSER: Learning Better Representations for Richly Structured Emails
Furkan Kocayusufoğlu
Nguyen Ha Vo
Proceedings of the 2019 World Wide Web Conference, pp. 886-895
Anatomy of a Privacy-Safe Large-Scale Information Extraction System Over Email
24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, ACM (2018), pp. 734-743
Learning Effective Embeddings for Machine Generated Emails with Applications to Email Category Prediction
Yu Sun
Luis Garcia Pueyo
Proceedings of the IEEE International Conference on Big Data (2018), pp. 1846-1855
