Unifying Structured Data as Graph for Data-to-Text Pre-Training
Abstract Data-to-text (D2T) generation aims to transform structured data into natural
language text. Data-to-text pre-training has proved to be powerful in enhancing D2T …
language text. Data-to-text pre-training has proved to be powerful in enhancing D2T …
Retrieval-augmented generation with graphs (graphrag)
Retrieval-augmented generation (RAG) is a powerful technique that enhances downstream
task execution by retrieving additional information, such as knowledge, skills, and tools from …
task execution by retrieving additional information, such as knowledge, skills, and tools from …
KGCDP-T: Interpreting knowledge graphs into text by content ordering and dynamic planning with three-level reconstruction
Abstract Knowledge graph-to-text (KG-to-text) interpretation is employed to interpret given
KG into semantically coherent and logically reasonable text to enhance the applicability of …
KG into semantically coherent and logically reasonable text to enhance the applicability of …
Enhancing text generation from knowledge graphs with cross-structure attention distillation
X Shi, Z Xia, P Cheng, Y Li - Engineering Applications of Artificial …, 2024 - Elsevier
Existing Large-scale pre-trained language models (PLMs) can effectively enhance the
knowledge-graph-to-text (KG-to-text) generation by processing the linearized version of a …
knowledge-graph-to-text (KG-to-text) generation by processing the linearized version of a …
Improving plms for graph-to-text generation by relational orientation attention
T Wang, B Shen, J Zhang, Y Zhong - Neural Processing Letters, 2023 - Springer
Pretrained language models (PLMs) with impressive performances in graph-to-text
generation have recently been employed. However, linearized graph data will lead to the …
generation have recently been employed. However, linearized graph data will lead to the …
Metrics of Graph-Based Meaning Representations with Applications from Parsing Evaluation to Explainable NLG Evaluation and Semantic Search
J Opitz - 2024 - archiv.ub.uni-heidelberg.de
" Who does what to whom?" The goal of a graph-based meaning representation (in short:
MR) is to represent the meaning of a text in a structured format. With an MR, we can …
MR) is to represent the meaning of a text in a structured format. With an MR, we can …
Integrating Relational Structure to Heterogeneous Graph for Chinese NL2SQL Parsers
C Ma, W Zhang, M Huang, S Feng, Y Wu - Electronics, 2023 - mdpi.com
The existing models for NL2SQL tasks are mainly oriented toward English text and cannot
solve the problems of column name reuse in Chinese text data, description in natural …
solve the problems of column name reuse in Chinese text data, description in natural …