Date: Fri, 29 Mar 2024 04:37:40 +0000 (UTC) Message-ID: <1205303536.237.1711687060164@1a5b09e72cd8> Subject: Exported From Confluence MIME-Version: 1.0 Content-Type: multipart/related; boundary="----=_Part_236_1673716892.1711687060163" ------=_Part_236_1673716892.1711687060163 Content-Type: text/html; charset=UTF-8 Content-Transfer-Encoding: quoted-printable Content-Location: file:///C:/exported.html
Tutorial at AJCAI 2022 ("A Practical Guide to Knowledge Graph Const= ruction from Technical Short Text"). Abstract below:
Have you ever wo= ndered how to harness the significant volume of knowledge buried within uns= tructured text? Approximately 80% of all data in organisations is unstructu= red, a large portion of which exists in the form of technical language such= as doctor's notes, maintenance work orders, and traffic reports. Natural L= anguage Processing (NLP) provides the means to construct knowledge graphs f= rom unstructured short text, enabling the querying of knowledge held within= the text. Knowledge graphs are employed by a wide range of top companies = =E2=80=93 eBay, Walmart and Volvo to name a few. But what exactly is a know= ledge graph? Why are leading companies actively building knowledge graphs, = and how is one created?
This tutorial provides a practical guide to k= nowledge graphs. We will begin by providing an overview of graph databases,= highlighting their unique advantages when compared to structured data mode= ls such as relational tables. We will then detail the underlying natural la= nguage processing techniques involved in knowledge graph construction from = text, namely named entity recognition (NER) and relation extraction (RE). W= e will motivate the need for knowledge graphs via a simple, practical examp= le in the maintenance domain. This Python notebook-based example will demon= strate how noisy, unstructured text such as maintenance work orders can be = transformed into a knowledge graph to visualise and query unstructured data= and allow domain experts to make informed business decisions.