TY  - CONF
ID  - SisLab3511
UR  - https://dl.acm.org/citation.cfm?id=3310999
A1  - Nguyen, Minh Trang
A1  - Tran, Van Lien
A1  - Can, Duy Cat
A1  - Ha, Quang Thuy
A1  - Vu, Thi Ly
A1  - Chng, Eng-Siong
Y1  - 2019/01/25/
N2  - For information consumers, being able to obtain a short and accurate answer for a query is one of the most desirable features. This motivation, along with the rise of deep learning, has led to a boom in open-domain Question Answering (QA) research. While the problem of machine comprehension has received multiple success with the help of large training corpora and the emergence of attention mechanism, the development of document retrieval in open-domain QA is lagged behind. In this work, we propose a novel encoding method for learning question-aware self-attentive document representations. By applying pair-wise ranking approach to these encodings, we build a Document Retriever, called QASA, which is then integrated with a machine reader to form a complete open-domain QA system. Our system is thoroughly evaluated using QUASAR-T dataset and shows surpassing results compared to other state-of-the-art methods.
PB  - ACM New York, NY, USA ©2019
SN  - 978-1-4503-6612-0 doi>10.1145/3310986.3310999
TI  - QASA: Advanced Document Retriever for Open-Domain Question Answering by Learning to Rank Question-Aware Self-Attentive Document Representations
M2  - Da Lat, Vietnam
AV  - restricted
EP  - 5
T2  - The 3rd International Conference on Machine Learning and Soft Computing
ER  -