Jin Y.
About Jin Y.
Jin Y. Research Scientist
Jin Y. is an accomplished research scientist specializing in natural language processing (NLP) and machine learning. Leveraging advanced computational techniques, Jin has made significant contributions to text classification, contextual targeting, and language generation. Jin’s expertise is recognized in various prestigious conferences and workshops, marking a notable presence in the field.
Publications and Research
Jin Y. has an extensive publication record, showcasing research across diverse aspects of natural language processing. Key publications include 'Towards Weakly-Supervised Hate Speech Classification Across Datasets' in the 7th Workshop on Online Abuse and Harms (WOAH 2023), and 'Seed Word Selection for Weakly-Supervised Text Classification with Unsupervised Error Estimation' presented at the 2021 Conference of the North American Chapter of the Association for Computational Linguistics. Jin's work on 'Learning from noisy out-of-domain corpus using dataless classification' and 'Towards Improving Coherence and Diversity of Slogan Generation' has been featured in Natural Language Engineering as well.
Conference Presentations
Jin Y.'s research contributions have been presented at numerous influential conferences. Notable presentations include 'Plot Writing From Pre-Trained Language Models' and 'Automated Ad Creative Generation' both at the 15th International Conference on Natural Language Generation (INLG). Additionally, Jin co-authored 'Bootstrapping Large-Scale Fine-Grained Contextual Advertising Classifier from Wikipedia' presented at the Fifteenth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-15)
Patents: Cross-Domain Contextual Targeting
Jin Y. holds a U.S. patent for 'Cross-domain contextual targeting without any in-domain labelled data.' This patent reflects Jin’s innovative approach to solving complex machine learning problems, aiming to enhance contextual advertising by leveraging cross-domain knowledge without the necessity of labelled data from the target domain.
Impactful Contributions in NLP
Jin Y. has co-authored and presented various impactful papers that contribute to the advancement of natural language processing. 'Learning Only from Relevant Keywords and Unlabeled Documents,' presented at the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), is a testament to Jin’s focus on effective and precise text classification. Publications like 'Bridging the Gap Between Research and Production with CODE' reflect practical solutions bridging theoretical research and real-world applications.