Roselyne Tchoua (University of Chicago), Aswathy Ajith (University of Chicago), Zhi Hong (University of Chicago), Logan Ward (Argonne National Laboratory), Kyle Chard (University of Chicago), Debra Audus (National Institute of Standards and Technology), Shrayesh Patel (University of Chicago), Juan de Pablo (University of Chicago), and Ian Foster (Argonne National Laboratory)
Despite significant progress in natural language processing, machine learning models require substantial expert annotated training data to perform well in tasks such as named entity recognition (NER) and entity relations extraction. Furthermore, NER is often more complicated when working with scientific text. For example, in polymer science, chemical structure may be encoded using nonstandard naming conventions, the same concept can be expressed using many different terms (synonymy), and authors may refer to polymers with ad-hoc labels. These challenges, which are not unique to polymer science, make it difficult to generate training data, as specialized skills are needed to label text correctly. We have previously designed polyNER, a semi-automated system for efficient identification of scientific entities in text. PolyNER applies word embedding models to generate entity-rich corpora for productive expert labeling, and then uses the resulting labeled data to bootstrap a context-based word vector classifier. PolyNER facilitates a labeling process that is otherwise tedious and expensive. Here, we use active learning to efficiently obtain more annotations from experts and improve performance. PolyNER requires just five hours of expert time to achieve discrimination capacity comparable to that of a state-of-the-art chemical natural language processing toolkit, highlighting the potential for human-computer partnership in domain-specific scientific NER.
