Events Calendar

PhD Preliminary Oral Exam – Reza Ghaeini

Improving and Understanding Deep Models for Natural Language Comprehension

Natural Language Comprehension is a challenging domain of Natural Language Processing. To improve a model's language comprehension/understanding, a possible approach would be enriching the structure of the model to enhance its capability to learn the latent rules of the language. In this thesis, I will first introduce several deep models for a variety of natural language comprehension tasks including natural language inference and question answering. These models yield better empirical performances, however, due to the black-box nature of deep learning, it is difficult to assess whether the improved models indeed acquire a better understanding of language. Meanwhile, data is often plagued by meaningless or even harmful statistical biases and deep models might achieve high performance by focusing on the biases. This motivates us to study methods for ``peaking inside'' the black-box deep models to provide explanation and understanding of the models’ behavior. Further, we introduce a novel mechanism (saliency learning), which learns from ground-truth explanation signal such that the learned model will not only make the right prediction but also for the right reason. Our experimental results on multiple tasks and datasets demonstrate the effectiveness of the proposed methods, which produce more reliable predictions while delivering better results compared to traditionally trained models. Going forward, we will study and validate reliability of the proposed explanation methods for deep models.

Major Advisor: Xiaoli Fern
Committee: Prasad Tadepalli
Committee: Liang Huang
Committee: David Hendrix
GCR: Len Coop

Tuesday, May 28 at 11:00am to 1:00pm

Kelley Engineering Center, 1007
110 SW Park Terrace, Corvallis, OR 97331

Event Type

Lecture or Presentation

Event Topic


Electrical Engineering and Computer Science
Contact Name

Calvin Hughes

Contact Email

Google Calendar iCal Outlook

Recent Activity