자연어 질의응답 시스템과 관련한 이전의 연구들은 주어진 질문과 단락으로부터 정확한 정답을 추출하는 문제에 초점을 맞추고 있다. 그러나, 기계독해에서 오픈 도메인 질의응답으로 문제를 확장하였을 때, 정답이 포함된 단락을 잘 찾는 것이 기계독해 못지않은 중요한 요소이다. DrQA[1]에서는 초기 검색 단계를 포함하여 질의응답을 하였을 때 Exact Match@Top1 성능이 69.5%에서 27.1%로 하락했다고 평가하였다. 본 논문에서는 질의응답 시스템 성능 향상을 위해 2단계 단락 재순위화 모델을 제안한다. 2단계 단락 재순위화 모델은 심볼릭 순위화 모델과 뉴럴 순위화 모델의 결과를 통합하여 다시 재순위화하는 모델이다. 심볼릭 순위화 모델은 CatBoost 알고리즘과 질문과 단락 간의 자질을 기반으로 단락을 순위화하고, 뉴럴 순위화 모델은 한국어 딥러닝 언어모델(KorBERT)을 사후학습하여 순위화하였다. 2단계 모델은 뉴럴 리그레션 모델에 기반하여 순위화하였다. 본 논문에서는 특징이 다른 순위화 모델을 결합하여 성능을 극대화하였고, 최종적으로 제안한 모델은 1,000건의 질문을 평가하였을 때 MRR 기준 85.8%과 BinaryRecall@Top1기준 82.2%의 성능을 보였고, 각 성능은 베이스라인 모델보다 17.3%(MRR), 22.3% (BR@Top1)이 향상되었다.
KSP Keywords
Exact match
Copyright Policy
ETRI KSP Copyright Policy
The materials provided on this website are subject to copyrights owned by ETRI and protected by the Copyright Act. Any reproduction, modification, or distribution, in whole or in part, requires the prior explicit approval of ETRI. However, under Article 24.2 of the Copyright Act, the materials may be freely used provided the user complies with the following terms:
The materials to be used must have attached a Korea Open Government License (KOGL) Type 4 symbol, which is similar to CC-BY-NC-ND (Creative Commons Attribution Non-Commercial No Derivatives License). Users are free to use the materials only for non-commercial purposes, provided that original works are properly cited and that no alterations, modifications, or changes to such works is made. This website may contain materials for which ETRI does not hold full copyright or for which ETRI shares copyright in conjunction with other third parties. Without explicit permission, any use of such materials without KOGL indication is strictly prohibited and will constitute an infringement of the copyright of ETRI or of the relevant copyright holders.
J. Kim et. al, "Trends in Lightweight Kernel for Many core Based High-Performance Computing", Electronics and Telecommunications Trends. Vol. 32, No. 4, 2017, KOGL Type 4: Source Indication + Commercial Use Prohibition + Change Prohibition
J. Sim et.al, “the Fourth Industrial Revolution and ICT – IDX Strategy for leading the Fourth Industrial Revolution”, ETRI Insight, 2017, KOGL Type 4: Source Indication + Commercial Use Prohibition + Change Prohibition
If you have any questions or concerns about these terms of use, or if you would like to request permission to use any material on this website, please feel free to contact us
KOGL Type 4:(Source Indication + Commercial Use Prohibition+Change Prohibition)
Contact ETRI, Research Information Service Section
Privacy Policy
ETRI KSP Privacy Policy
ETRI does not collect personal information from external users who access our Knowledge Sharing Platform (KSP). Unathorized automated collection of researcher information from our platform without ETRI's consent is strictly prohibited.
[Researcher Information Disclosure] ETRI publicly shares specific researcher information related to research outcomes, including the researcher's name, department, work email, and work phone number.
※ ETRI does not share employee photographs with external users without the explicit consent of the researcher. If a researcher provides consent, their photograph may be displayed on the KSP.