Graduate Thesis Or Dissertation

 

Domain Adaptation for Factoid Question Answering Public Deposited

Downloadable Content

Download PDF
https://scholar.colorado.edu/concern/graduate_thesis_or_dissertations/7m01bm06q
Abstract
  • Most results in supervised learning make the assumption that the distributions from which the training data and test data are are drawn are independent and identically distributed. In practice, knowledge is stored in many different forms, and models that can combine information from multiple sources have an advantage over those that are restricted by the i.i.d. assumption. In this work, we present results on a factoid question answering dataset with 91754 questions representing 15400 different answers, and demonstrate significant improvement in accuracy by augmenting the training set with raw text from Wikipedia. In particular the most pronounced gains in accuracy are concentrated on the answers which have low representation in the training set. This is accomplished by using deep averaging networks (DANs), which we empirically demonstrate can learn in this heterogeneous setting, with no modifications, making them an attractive option compared to the other more complex methods for domain adaptation which are often used.
Creator
Date Issued
  • 2017
Academic Affiliation
Advisor
Committee Member
Degree Grantor
Commencement Year
Subject
Last Modified
  • 2019-11-17
Resource Type
Rights Statement
Language

Relationships

Items