Expertise
Natural Language Processing, Machine Learning, Health Informatics
Research Interests
Natural Language Processing, Machine Learning, Health Informatics
Hadi Amiri's primary research interest is in Natural Language Processing (NLP) – an AI-complete problem concerned with understanding human language through computers. He approaches NLP problems through findings in cognitive psychology about learning, memory, attention, and language use in humans. In terms of applications, he is interested in building NLP and Machine Learning systems that tackle health-related challenges in diagnostic and therapeutic decision-making.
Education
- Postdoc: Department of Biomedical Informatics (DBMI), (2020), Harvard University
- Postdoc: Department of Computer Science, (2016), University of Maryland, College Park
- Ph D: Department of Computer Science, (2013), National University of Singapore
Dissertation/Thesis Title: Making Sense of Micro-posts for Organizations and Businesses: Live Event and User Community Detection - MS: Department of Electrical and Computer Engineering, (2008), University of Tehran
Dissertation/Thesis Title: Distributed Information Retrieval on the Web
Selected Publications
- Amiri, H. (2019). Neural Self-Training through Spaced Repetition. Proceedings of the 2019 Conference of the North American Association for Computational Linguistics (NAACL'19)
- Hajipoor, H., Amiri, H., Rahgozar, M., Oroumchian, F. (2019). Serial Recall Effects in Neural Language Modeling. Proceedings of the 2019 Conference of the North American Association for Computational Linguistics (NAACL'19)
- Amiri, H., Mohtarami, M. (2019). Vector of Locally Aggregated Embeddings for Text Representation. Proceedings of the 2019 Conference of the North American Association for Computational Linguistics (NAACL'19)
- Amiri, H., Miller, T., Savova, G. (2018). Spotting Spurious Data with Neural Networks. Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL'18)
- Amiri, H., Magane, K., Wisk, L., Savova, G., Weitzman, E. (2018). Toward Large-scale and Multi-facet Analysis of First-person Alcohol Drinking. American Medical Informatics Association (AMIA'18)
- Amiri, H., Miller, T., Savova, G. (2017). Repeat before Forgetting: Spaced Repetition for Efficient and Effective Training of Neural Networks. Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, Association for Computational Linguistics (EMNLP'17)
- Amiri, H., Resnik, P., Boyd-Graber, J., Daumé III, H. (2016). Learning Text Pair Similarity with Context-sensitive Autoencoders. Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (ACL'16)
- Amiri, H., Daumé III, H. (2016). Short Text Representation for Detecting Churn in Microblogs. Proceedings of the 30th Annual Meeting of the Association for the Advancement of Artificial Intelligence (AAAI'16)
- Amiri, H., Daumé III, H. (2015). Target-dependent Churn Classification in Microblogs. Proceedings of the 29th Annual Meeting of the Association for the Advancement of Artificial Intelligence (AAAI'15)
- Amiri, H., Zha, Z., Chua, T. (2013). A Pattern Matching Based Model for Implicit Opinion Question Identification. Proceedings of the 27th Annual Meeting of the Association for the Advancement of Artificial Intelligence (AAAI'13)
- Chen, Y., Amiri, H., Li, Z., Chua, T. (2013). Emerging topic detection for organizations from microblogs. Proceedings of the 36th international ACM SIGIR conference on Research and development in information retrieval (SIGIR'13)
- Amiri, H., Chua, T. (2012). Mining sentiment terminology through time. Proceedings of the 21st ACM international conference on Information and knowledge management (CIKM'12)
- Amiri, H., Chua, T. (2012). Mining slang and urban opinion words and phrases from cQA services. Proceedings of the fifth ACM international conference on Web search and data mining (WSDM'12)