질의응답에 대한 지식베이스 기반 근거 문장 생성 모델 = Knowledge-based Supporting Facts Generation Model for Question and Answer

다국어 초록 (Multilingual Abstract)

In this study, we intend to create supporting facts from the knowledge base to add information to the question and answer process, and provide a form that is easy for humans to read.
Data from two knowledge bases, DBpedia and Wikidata, related to supporting documents in HotpotQA were collected through crawling, and the supporting facts generators were trained using collected triples. The answer generator was trained with generated supporting facts and questions as inputs.
Regardless of both DBpedia and Wikidata, supporting facts generated based on the knowledge base improved answer generation performance by providing positive additional information about questions, and generated human-understandable sentences.

참고문헌 (Reference)

1 Z. Fu, "Unsupervised KB-to-Text Generation with Auxiliary Triple Extraction using Dual Learning" 258-268, 2020

2 C. Y. Lin, "ROUGE : A package for automatic evaluation of summaries" 74-81, 2004

3 S. Kwon, "RNN Based Natural Language Sentence Generation from a Knowledge Graph and Keyword Sequence" 425-429, 2018

4 M. Gardner, "Open-vocabulary semantic parsing with both distributional statistics and formal knowledge" 31 (31): 3195-3201, 2017

5 H. Sun, "Open domain question answering using early fusion of knowledge bases and text" 4231-4242, 2018

6 E. Chang, "Neural data-to-text generation with lm-based text augmentation" 758-768, 2021

7 R. Das, "Knowledge Base Question Answering by Case-based Reasoning over Subgraphs" 4777-4793, 2022

8 Z. Yang, "HotpotQA : A dataset for diverse, explainable multi-hop question answering" 2369-2380, 2018

9 A. See, "Get to the point : Summarization with pointer-generator networks" 1 : 1073-1083, 2017

10 C. Raffel, "Exploring the limits of transfer learning with a unified text-to-text transformer" 21 : 140-, 2020

11 M. Zhang, "Crake : Causal-Enhanced Table-Filler for Question Answering over Large Scale Knowledge Base" 1787-1798, 2022

12 K. Papineni, "Bleu : A method for automatic evaluation of machine translation" 311-318, 2002

13 V. I. Levenshtein, "Binary codes capable of correcting deletions, insertions, and reversals" 10 (10): 707-710, 1966

14 M. Lewis, "BART : Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension" 7871-7880, 2020