TA-DA: Topic-Aware Domain Adaptation for Scientific Keyphrase Identification and Classification (Student Abstract)

Keyphrase identification and classification is a Natural Language Processing Information Retrieval task that involves extracting relevant groups of words from given text related to the main topic. In this work, we focus on keyphrases scientific documents. We introduce TA-DA, Topic-Aware Domain Adaptation framework for keyphrase extraction integrates Multi-Task Learning with Adversarial Training Adaptation. Our approach improves performance over baseline models by up 5% in exact match F1-score.