06-19, 14:15–15:00 (Europe/London), Tower Suite 1
Dealing with unstructured text to obtain information is one of the biggest aims in the field of natural language processing. In this talk, we will be demoing a solution where we have unstructured text on a particular topic, and we apply named entity recognition, together with relationship extraction, to extract structured data. We will be introducing our data source, the models that we use, and will be inspecting the end results, viewing particular statistics, and hovering over a graph, extracted from the raw text.
Relationship extraction is an essential task within the field of NLP, when we want to obtain structured data from raw text, in relational format. When we are to extract an information graph from raw text alone, named entity recognition provides us with the nodes in the graph, while relationship extraction gives us the edges (relations) between the nodes. And yet, relationship extraction is not as widely presented and demonstrated as a task, within the broad NLP community. In this talk, we are aiming to demo a solution where we have a news-based data source, and we are trying to obtain information on a particular topic. We will be viewing the raw text, seeing exploratory data analysis results, and moving on to see NER / Relex predictions taken on the data. Finally, we will be inspecting a graph that is formed based on the NER / Relex predictions that we have.
No previous knowledge expected
