Kimberly Lu
EECS Department
University of California, Berkeley
Technical Report No. UCB/EECS-2019-44
May 15, 2019
http://www2.eecs.berkeley.edu/Pubs/TechRpts/2019/EECS-2019-44.pdf
In this work we explore the usefulness and practicality of domain adaptation and multi-domain learning methods in question-answer generation. Unlike recent work in question-answer generation which focuses on processing single-domain data to create synthetic reading comprehension datasets (Du and Cardie, 2018), we propose a question-answer generation system that can adapt to datasets containing multiple domains while still achieving similar or better performance in single domains compared to a baseline. We apply our system, consisting of an answer extraction system and a question generation system, to the SQuAD and SciQ reading comprehension datasets and evaluate its efficacy in mixed- and single-domain settings. Our domain adaptation method achieves higher performance than baselines on the mixed-domain and SciQ datasets in both answer extraction and question generation.
Advisor: Dawn Song
BibTeX citation:
@mastersthesis{Lu:EECS-2019-44, Author = {Lu, Kimberly}, Title = {Multiple Domain Question-Answer Generation}, School = {EECS Department, University of California, Berkeley}, Year = {2019}, Month = {May}, URL = {http://www2.eecs.berkeley.edu/Pubs/TechRpts/2019/EECS-2019-44.html}, Number = {UCB/EECS-2019-44}, Abstract = {In this work we explore the usefulness and practicality of domain adaptation and multi-domain learning methods in question-answer generation. Unlike recent work in question-answer generation which focuses on processing single-domain data to create synthetic reading comprehension datasets (Du and Cardie, 2018), we propose a question-answer generation system that can adapt to datasets containing multiple domains while still achieving similar or better performance in single domains compared to a baseline. We apply our system, consisting of an answer extraction system and a question generation system, to the SQuAD and SciQ reading comprehension datasets and evaluate its efficacy in mixed- and single-domain settings. Our domain adaptation method achieves higher performance than baselines on the mixed-domain and SciQ datasets in both answer extraction and question generation.} }
EndNote citation:
%0 Thesis %A Lu, Kimberly %T Multiple Domain Question-Answer Generation %I EECS Department, University of California, Berkeley %D 2019 %8 May 15 %@ UCB/EECS-2019-44 %U http://www2.eecs.berkeley.edu/Pubs/TechRpts/2019/EECS-2019-44.html %F Lu:EECS-2019-44