About This Document
- sl:arxiv_author :
- sl:arxiv_firstAuthor : Seunghak Yu
- sl:arxiv_num : 2008.08995
- sl:arxiv_published : 2020-08-20T14:30:33Z
- sl:arxiv_summary : Knowledge graphs (KGs) are relevant to many NLP tasks, but building a
reliable domain-specific KG is time-consuming and expensive. A number of
methods for constructing KGs with minimized human intervention have been
proposed, but still require a process to align into the human-annotated
knowledge base. To overcome this issue, we propose a novel method to
automatically construct a KG from unstructured documents that does not require
external alignment and explore its use to extract desired information. To
summarize our approach, we first extract knowledge tuples in their surface form
from unstructured documents, encode them using a pre-trained language model,
and link the surface-entities via the encoding to form the graph structure. We
perform experiments with benchmark datasets such as WikiMovies and MetaQA. The
experimental results show that our method can successfully create and search a
KG with 18K documents and achieve 69.7% hits@10 (close to an oracle model) on a
query retrieval task.@en
- sl:arxiv_title : Constructing a Knowledge Graph from Unstructured Documents without External Alignment@en
- sl:arxiv_updated : 2020-08-20T14:30:33Z
- sl:bookmarkOf : https://arxiv.org/abs/2008.08995
- sl:creationDate : 2020-08-21
- sl:creationTime : 2020-08-21T18:38:32Z
Documents with similar tags (experimental)