Sneha is a Software Development Engineer with the Personalization team at Amazon. Her work involves using customer behavior data to guide hypothesis-driven experimentation and developing highly personalized recommendation experiences for Amazon customers. She holds a Master’s degree in Computer Science (Machine Learning) from the University of Pennsylvania. She’s passionate about AI and working with data. Her research focus at Penn was in the fields of Machine Learning, Natural Language Processing, and Deep Learning. She has presented her research at notable conferences like the Annual Meeting of the Association for Computational Linguistic, Mid-Atlantic Student Colloquium on Speech, Language and Learning, Grace Hopper Celebration for Women in Computing, GDG Dev Fest, and AlterConf.
Upcoming Abstract Summary
Deep Learning Architectures for Semantic Relation Detection Tasks
Recognizing and distinguishing specific semantic relations from other types of semantic relations is an essential part of language understanding systems. Identifying expressions with similar and contrasting meanings is valuable for NLP systems which go beyond recognizing semantic relatedness and require to identify specific semantic relations. In this talk, I will first present novel techniques for creating labelled datasets required for training deep learning models for classifying semantic relations between phrases. I will further present various neural network architectures that integrate morphological features into integrated path-based and distributional relation detection algorithms and demonstrate that this model outperforms state-of-the-art models in distinguishing semantic relations and is capable of efficiently handling multi-word expressions.