RISS 학술연구정보서비스

검색

인기 검색어

    다국어 입력

    http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.

    변환된 중국어를 복사하여 사용하시면 됩니다.

    예시)
    • 中文 을 입력하시려면 zhongwen을 입력하시고 space를누르시면됩니다.
    • 北京 을 입력하시려면 beijing을 입력하시고 space를 누르시면 됩니다.
    닫기
    KCI우수등재

    R2FID: Joint Reranker기반 Fusion-In-Decoder를 이용한 오픈 도메인 테이블 질의 응답 = R2 FID: Joint Reranker in Fusion-In-Decoder for Open Domain Question Answering over Tables

    한글로보기

    https://www.riss.kr/link?id=A108788234

    • 0

      상세조회
    • 0

      다운로드
    서지정보 열기
    • 내보내기
    • 내책장담기
    • 공유하기
    • 오류접수
    인용문이 복사되었습니다.

    부가정보

    다국어 초록 (Multilingual Abstract) kakao i 다국어 번역

    Open Domain Question Answering is a challenging problem that aims to generate an answer where reference documents relevant to a question are not provided. Considering that the importance of the QA system in structured data such as tables has recently gradually increased, this paper presents a method for table open domain question answering of Korean, focusing on tabular contents appearing in Wikipedia. In addition, we extensively apply the Joint Reranker based Fusion-In-Decoder to address limitations entailed in table retrieval, Resulting methods based on Joint Reranker led to improvements of an EM of 3.36 and a F1-Score of 3.25 over open domain question answering tasks.
    번역하기

    Open Domain Question Answering is a challenging problem that aims to generate an answer where reference documents relevant to a question are not provided. Considering that the importance of the QA system in structured data such as tables has recently ...

    Open Domain Question Answering is a challenging problem that aims to generate an answer where reference documents relevant to a question are not provided. Considering that the importance of the QA system in structured data such as tables has recently gradually increased, this paper presents a method for table open domain question answering of Korean, focusing on tabular contents appearing in Wikipedia. In addition, we extensively apply the Joint Reranker based Fusion-In-Decoder to address limitations entailed in table retrieval, Resulting methods based on Joint Reranker led to improvements of an EM of 3.36 and a F1-Score of 3.25 over open domain question answering tasks.

    더보기

    참고문헌 (Reference)

    1 J. Yang, "TableFormer: Robust transformer modeling for table-text encoding" 1 : 528-537, 2022

    2 J. Herzig, "TaPas: Weakly supervised table parsing via pre-training" 4320-4333, 2020

    3 F. Zhu, "Retrieving and reading : A comprehensive survey on open-domain question answering" CoRR 2021

    4 W. Zhong, "Reasoning over hybrid chain for tableand-text open domain question answering" 7 : 4531-4537, 2022

    5 D. Chen, "Reading Wikipedia to answer open-domain questions" 1870-1879, 2017

    6 W. Chen, "Open question answering over tables and text" CoRR 2020

    7 Y. Feng, "Multi-hop open-domain question answering over structured and unstructured knowledge" 151-156, 2022

    8 G. Izacard, "Leveraging passage retrieval with generative models for open domain question answering" 874-880, 2021

    9 C. Jun, "Korean-specific dataset for table question answering" 2022

    10 김영민 ; 임승영 ; 이현정 ; 박소윤 ; 김명지, "KorQuAD 2.0: 웹문서 기계독해를 위한 한국어 질의응답 데이터셋" 한국정보과학회 47 (47): 577-586, 2020

    1 J. Yang, "TableFormer: Robust transformer modeling for table-text encoding" 1 : 528-537, 2022

    2 J. Herzig, "TaPas: Weakly supervised table parsing via pre-training" 4320-4333, 2020

    3 F. Zhu, "Retrieving and reading : A comprehensive survey on open-domain question answering" CoRR 2021

    4 W. Zhong, "Reasoning over hybrid chain for tableand-text open domain question answering" 7 : 4531-4537, 2022

    5 D. Chen, "Reading Wikipedia to answer open-domain questions" 1870-1879, 2017

    6 W. Chen, "Open question answering over tables and text" CoRR 2020

    7 Y. Feng, "Multi-hop open-domain question answering over structured and unstructured knowledge" 151-156, 2022

    8 G. Izacard, "Leveraging passage retrieval with generative models for open domain question answering" 874-880, 2021

    9 C. Jun, "Korean-specific dataset for table question answering" 2022

    10 김영민 ; 임승영 ; 이현정 ; 박소윤 ; 김명지, "KorQuAD 2.0: 웹문서 기계독해를 위한 한국어 질의응답 데이터셋" 한국정보과학회 47 (47): 577-586, 2020

    11 P. Rajpurkar, "Know what you don’t know : Unanswerable questions for SQuAD" 784-789, 2018

    12 S. Park, "KLUE : korean language understanding evaluation" 2021

    13 D. Yu, "KG-FiD: Infusing knowledge graph in fusion-in-decoder for open-domain question answering" 4961-4974, 2022

    14 W. Chen, "HybridQA: A dataset of multihop question answering over tabular and textual data" 1026-1036, 2020

    15 S. Wang, "Evidence aggregation for answer reranking in open-domain question answering" CoRR 2017

    16 V. Karpukhin, "Dense passage retrieval for open-domain question answering" 6769-6781, 2020

    17 Y. Luo, "A survey : Complex knowledge base question answering" 46-52, 2022

    더보기

    분석정보

    View

    상세정보조회

    0

    Usage

    원문다운로드

    0

    대출신청

    0

    복사신청

    0

    EDDS신청

    0

    동일 주제 내 활용도 TOP

    더보기

    주제

    연도별 연구동향

    연도별 활용동향

    연관논문

    연구자 네트워크맵

    공동연구자 (7)

    유사연구자 (20) 활용도상위20명

    이 자료와 함께 이용한 RISS 자료

    나만을 위한 추천자료

    해외이동버튼