Knowgl: Knowledge generation and linking from text

G Rossiello, MFM Chowdhury… - Proceedings of the …, 2023 - ojs.aaai.org
We propose KnowGL, a tool that allows converting text into structured relational data
represented as a set of ABox assertions compliant with the TBox of a given Knowledge …

A universal question-answering platform for knowledge graphs

R Omar, I Dhall, P Kalnis, E Mansour - … of the ACM on Management of …, 2023 - dl.acm.org
Knowledge from diverse application domains is organized as knowledge graphs (KGs) that
are stored in RDF engines accessible in the web via SPARQL endpoints. Expressing a well …

Harnessing Knowledge and Reasoning for Human-Like Natural Language Generation: A Brief Review

J Chen, Y Xiao - arXiv preprint arXiv:2212.03747, 2022 - arxiv.org
The rapid development and application of natural language generation (NLG) techniques
has revolutionized the field of automatic text production. However, these techniques are still …

Applying a generic sequence-to-sequence model for simple and effective keyphrase generation

MFM Chowdhury, G Rossiello, M Glass… - arXiv preprint arXiv …, 2022 - arxiv.org
In recent years, a number of keyphrase generation (KPG) approaches were proposed
consisting of complex model architectures, dedicated training paradigms and decoding …

Knowledge graph induction enabling recommending and trend analysis: a corporate research community use case

N Mihindukulasooriya, M Sava, G Rossiello… - International Semantic …, 2022 - Springer
A research division plays an important role of driving innovation in an organization. Drawing
insights, following trends, keeping abreast of new research, and formulating strategies are …

SPARKLE: Enhancing SPARQL Generation with Direct KG Integration in Decoding

J Lee, H Shin - arXiv preprint arXiv:2407.01626, 2024 - arxiv.org
Existing KBQA methods have traditionally relied on multi-stage methodologies, involving
tasks such as entity linking, subgraph retrieval and query structure generation. However …

[PDF][PDF] The combination of BERT and data oversampling for answer type prediction

TT Hoang, OE Ojo, OO Adebanji, H Calvo… - Proceedings of the …, 2022 - ceur-ws.org
In this paper, we address the Task 1 (of the SMART Task 2021) of predicting the answer
categories and types based on target ontologies, which could be useful in knowledge-based …

Hierarchical pattern-based complex query of temporal knowledge graph

L Zhu, H Zhang, L Bai - Knowledge-Based Systems, 2024 - Elsevier
The complex query is an essential type of knowledge graph query, which aims to deal with
the complex relationships among multiple triples involved in query problems. However, the …

Learning to transpile AMR into SPARQL

M Bornea, RF Astudillo, T Naseem… - arXiv preprint arXiv …, 2021 - arxiv.org
We propose a transition-based system to transpile Abstract Meaning Representation (AMR)
into SPARQL for Knowledge Base Question Answering (KBQA). This allows us to delegate …

Semi-Structured Chain-of-Thought: Integrating Multiple Sources of Knowledge for Improved Language Model Reasoning

X Su, T Le, S Bethard, P Howard - arXiv preprint arXiv:2311.08505, 2023 - arxiv.org
An important open question pertaining to the use of large language models for knowledge-
intensive tasks is how to effectively integrate knowledge from three sources: the model's …