Events

PhD Defense

Knowledge-Intensive and Entity-Centric Natural Language Processing

 

Download as iCal file

Tuesday, August 26, 2025, 09:00am - 11:00am
 

Speaker: Wenzheng Zhang

Bio

Location : CoRE 301

Committee: 

Professor Karl Stratos (advisor)

Associate Professor Abdeslam Boularias

Assistant Professor Hao Wang

Associate Professor Wei Xu

Event Type: PhD Defense

Abstract: Knowledge-intensive language processing and entity-centric language understanding are critical capabilities for modern natural language processing (NLP) systems. These abilities enable models to retrieve, integrate, and reason over large-scale external information while maintaining consistent interpretations of real-world entities. This presentation explores methods that enhance retrieval-based modeling and entity-level understanding, advancing performance on tasks such as information retrieval, retrieval-augmented generation, entity linking, and coreference resolution. In the first part, we focus on knowledge-intensive language processing. We begin with a theoretical analysis of hard negatives in the Noise Contrastive Estimation (NCE) training objective, then extend NCE to support multi-label retrieval, propose an approach to improve multi-task retrieval by encouraging task specialization, and finally introduce a retrieval-augmented generation framework that leverages implicit queries instead of human-specified ones. In the second part, we shift to entity-centric language understanding. We present a method that reformulates entity linking as an inverse open-domain question answering problem, avoiding the dilemma of predicting mentions without knowing their corresponding entities. We also propose an extremely simple yet high-performing sequence-to-sequence formulation for coreference resolution that maps input text to linearized coreference annotations. Together, these methods advance the development of NLP systems capable of deeper knowledge integration and entity-level understanding.

Organization: 

Contact  Professor Karl Stratos

Zoom Link: https://rutgers.zoom.us/j/96429315542?pwd=sBWkavz1jjzPFABZ8GVNFGWgh8PzJ2.1