eprintid: 3474
rev_number: 7
eprint_status: archive
userid: 307
dir: disk0/00/00/34/74
datestamp: 2019-06-04 14:52:07
lastmod: 2019-06-04 14:52:07
status_changed: 2019-06-04 14:52:07
type: conference_item
metadata_visibility: show
creators_name: Nguyen, Thi Minh Trang
creators_name: Tran, Van Lien
creators_name: Can, Duy Cat
creators_name: Ha, Quang Thuy
creators_name: Vu, Thi Ly
creators_name: Chng, Eng Siong
creators_id: 14020768@vnu.edu.vn
creators_id: catcd@vnu.edu.vn
creators_id: thuyhq@vnu.edu.vn
creators_id: ASESChng@ntu.edu.sg
corp_creators: Faculty of Information Technology (FIT)
title: QASA: Advanced Document Retriever for Open-Domain Question Answering by Learning to Rank Question-Aware Self-Attentive Document Representations
ispublished: pub
subjects: IT
divisions: fac_fit
abstract: 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.
date: 2019-01
date_type: published
official_url: https://dl.acm.org/citation.cfm?id=3310999
full_text_status: none
pres_type: paper
pagerange: 221-225
event_title: ICMLSC 2019: the 3rd International Conference on Machine Learning and Soft Computing
event_location: Da Lat, Viet Nam
event_dates: 25 - 28 January 2019
event_type: conference
refereed: TRUE
citation:   Nguyen, Thi Minh Trang and Tran, Van Lien and Can, Duy Cat and Ha, Quang Thuy and Vu, Thi Ly and Chng, Eng Siong  (2019) QASA: Advanced Document Retriever for Open-Domain Question Answering by Learning to Rank Question-Aware Self-Attentive Document Representations.  In: ICMLSC 2019: the 3rd International Conference on Machine Learning and Soft Computing, 25 - 28 January 2019, Da Lat, Viet Nam.