Advancement: Leveraging Natural Language Understanding to Build Robust Question Answering Models

Speaker Name
Geetanjali Rakshit
Speaker Title
Computer Science Ph.D. Student
Speaker Organization
Computer Science Ph.D.
Start Time
End Time
Virtual Event

Join us on Zoom / Passcode: 387153

Abstract: To solve many of the current challenges in Question Answering (QA), there is a need to build more robust models that have a deep understanding of text. This work leverages the use of natural language as a meaning representation in downstream tasks like question answering. As a step towards this goal, I propose a method to convert text in the form of a sentence into natural question-answer pairs, using its abstract meaning representation, and develop a tool, AMR Sourced Questions (ASQ), to do this. Data generated from ASQ could be used to train neural models to convert a sentence into question answer meaning representation or vice versa, for any domain. QA models have been shown to be sensitive to the choice of words in the questions, with a drop in performance when the questions are paraphrased. Towards addressing this performance gap, I propose to automatically create rich annotations on top of an existing QA dataset, in which the text containing the answer is paraphrased in a sequence of natural language steps deriving the answer. With this data, I propose to build neural models that learn to do more than surface-level processing of text and can handle paraphrases, with the aim of performing better than competitive baselines. As a third contribution, in my current work I demonstrate that state-of-the-art question answering models may be ranked improperly due to annotation errors in the evaluation sets. I propose a more rigorous and careful automatic evaluation method where predicted answers are evaluated against an exhaustive set of ground-truth answers, and present a human analysis of incorrect answers predicted by various QA models.

Event Type
Jeffrey Flanigan
Graduate Program
Computer Science Ph.D.