eprintid: 4492
rev_number: 8
eprint_status: archive
userid: 383
dir: disk0/00/00/44/92
datestamp: 2021-06-20 05:07:07
lastmod: 2021-06-20 05:07:07
status_changed: 2021-06-20 05:07:07
type: conference_item
metadata_visibility: show
creators_name: Le, Hoang Quynh
creators_name: Vuong, Thi Hai Yen
creators_name: Nguyen, Minh Trang
creators_id: lhquynh@vnu.edu.vn
creators_id: yenvth@vnu.edu.vn
creators_id: trangnm@vnu.edu.vn
title: UETfishes at MEDIQA 2021: Standing-on-the-Shoulders-of-Giants Model for Abstractive Multi-answer Summarization
ispublished: pub
subjects: ElectronicsandComputerEngineering
divisions: fac_fit
abstract: This paper describes a system developed to
summarize multiple answers challenge in the
MEDIQA 2021 shared task collocated with
the BioNLP 2021 Workshop. We present
an abstractive summarization model based
on BART, a denoising auto-encoder for pre�training sequence-to-sequence models. As focusing on the summarization of answers to consumer health questions, we propose a query-driven filtering phase to choose useful information from the input document automat�ically. Our approach achieves potential results, rank no.2 (evaluated on extractive references) and no.3 (evaluated on abstractive references)
in the final evaluation.
date: 2021
date_type: published
full_text_status: public
pres_type: paper
event_title: BioNLP-NAACL 2021
event_type: workshop
refereed: TRUE
citation:   Le, Hoang Quynh and Vuong, Thi Hai Yen and Nguyen, Minh Trang  (2021) UETfishes at MEDIQA 2021: Standing-on-the-Shoulders-of-Giants Model for Abstractive Multi-answer Summarization.  In: BioNLP-NAACL 2021.     
document_url: https://eprints.uet.vnu.edu.vn/eprints/id/eprint/4492/1/UETfishes_at_MEDIQA_2021__Standing_on_the_Shoulders_of_Giants_Model_for_Abstractive_Multi_answer_Summarization.pdf