Partially-aligned data-to-text generation with distant supervision

Z Fu, B Shi, W Lam, L Bing, Z Liu - arXiv preprint arXiv:2010.01268, 2020 - arxiv.org
The Data-to-Text task aims to generate human-readable text for describing some given
structured data enabling more interpretability. However, the typical generation task is …

Mitigating Knowledge Conflicts in Data-to-Text Generation via the Internalization of Fact Extraction

X Mo, Y Xiang, Y Pan, Y Hou… - 2024 International Joint …, 2024 - ieeexplore.ieee.org
Large Language Models (LLMs) have made remarkable advancements in Natural
Language Generation. Nonetheless, LLMs are prone to encountering knowledge conflicts …

Dynamic topic tracker for kb-to-text generation

F Zihao, L Bing, L Wai… - COLING 2020-28th …, 2020 - repository.essex.ac.uk
Recently, many KB-to-text generation tasks have been proposed to bridge the gap between
knowledge bases and natural language by directly converting a group of knowledge base …

질의응답에대한지식베이스기반근거문장생성모델

성수진차정원 - 정보과학회논문지, 2023 - dbpia.co.kr
본 연구에서는 지식베이스로부터 질의에 대한 근거 문장을 생성하여 응답 추론 과정에 정보를
추가하고, 사람이 읽기 쉬운 형태의 근거 문장을 제공하고자 한다. 이를 위해 HotpotQA 데이터 …

Open Domain Text Generation

Z Fu - 2021 - search.proquest.com
Text generation tasks see rapid growth during recent years. It aims to generate human-
readable text for describing some given input data enabling more interpretability for …