DataWords: Getting Contrarian with Text, Structured Data and Explanations
This addresses the challenge of integrating diverse data types for classification tasks, but it appears incremental as it adapts existing text methods to handle structured data without a major paradigm shift.
The paper tackles the problem of building classification models that combine free-text and structured data by representing structured data as text sentences called DataWords, enabling the use of text-modeling algorithms. The result shows improved text classification performance through examples where extraction tools convert structured data to DataWords and add them to the original text before classification.
Our goal is to build classification models using a combination of free-text and structured data. To do this, we represent structured data by text sentences, DataWords, so that similar data items are mapped into the same sentence. This permits modeling a mixture of text and structured data by using only text-modeling algorithms. Several examples illustrate that it is possible to improve text classification performance by first running extraction tools (named entity recognition), then converting the output to DataWords, and adding the DataWords to the original text -- before model building and classification. This approach also allows us to produce explanations for inferences in terms of both free text and structured data.