-
Exploiting Structured Knowledge in Text via Graph-Guided Representation Learning
In this work, we aim at equipping pre-trained language models with struc...
read it
-
JAKET: Joint Pre-training of Knowledge Graph and Language Understanding
Knowledge graphs (KGs) contain rich information about world knowledge, e...
read it
-
K-BERT: Enabling Language Representation with Knowledge Graph
Pre-trained language representation models, such as BERT, capture a gene...
read it
-
Using Local Knowledge Graph Construction to Scale Seq2Seq Models to Multi-Document Inputs
Query-based open-domain NLP tasks require information synthesis from lon...
read it
-
Hierarchical Neural Network for Extracting Knowledgeable Snippets and Documents
In this study, we focus on extracting knowledgeable snippets and annotat...
read it
-
Aspect-based Academic Search using Domain-specific KB
Academic search engines allow scientists to explore related work relevan...
read it
-
On Constructing a Knowledge Base of Chinese Criminal Cases
We are developing a knowledge base over Chinese judicial decision docume...
read it
Constructing a Knowledge Graph from Unstructured Documents without External Alignment
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 query retrieval task.
READ FULL TEXT
Comments
There are no comments yet.