-
IITP at MEDIQA 2019: Systems Report for Natural Language Inference, Question Entailment and Question Answering
This paper presents the experiments accomplished as a part of our partic...
read it
-
Self-Wiring Question Answering Systems
Question answering (QA) has been the subject of a resurgence over the pa...
read it
-
Supervised and Unsupervised Transfer Learning for Question Answering
Although transfer learning has been shown to be successful for tasks lik...
read it
-
Answering Complicated Question Intents Expressed in Decomposed Question Sequences
Recent work in semantic parsing for question answering has focused on lo...
read it
-
A Neural Question Answering System for Basic Questions about Subroutines
A question answering (QA) system is a type of conversational AI that gen...
read it
-
A Case Based Reasoning Approach for Answer Reranking in Question Answering
In this document I present an approach to answer validation and rerankin...
read it
Which Linguist Invented the Lightbulb? Presupposition Verification for Question-Answering
Many Question-Answering (QA) datasets contain unanswerable questions, but their treatment in QA systems remains primitive. Our analysis of the Natural Questions (Kwiatkowski et al. 2019) dataset reveals that a substantial portion of unanswerable questions (∼21 unverifiable presuppositions. We discuss the shortcomings of current models in handling such questions, and describe how an improved system could handle them. Through a user preference study, we demonstrate that the oracle behavior of our proposed system that provides responses based on presupposition failure is preferred over the oracle behavior of existing QA systems. Then we discuss how our proposed system could be implemented, presenting a novel framework that breaks down the problem into three steps: presupposition generation, presupposition verification and explanation generation. We report our progress in tackling each subproblem, and present a preliminary approach to integrating these steps into an existing QA system. We find that adding presuppositions and their verifiability to an existing model yields modest gains in downstream performance and unanswerability detection. The biggest bottleneck is the verification component, which needs to be substantially improved for the integrated system to approach ideal behavior – even transfer from the best entailment models currently falls short.
READ FULL TEXT
Comments
There are no comments yet.