Named Entity Recognition (NER) is a vital task in various NLP applications. However, in many real-world scenarios (e.g., voice-enabled assistants) new named entities are frequently introduced, entailing re-training NER models to support these new entities. Re-annotating the original training data for the new entities could be costly or even impossible when storage limitations or security concerns restrict access to that data, and annotating a new dataset for all of the entities becomes impractical and error-prone as the number of entities increases. To tackle this problem, we introduce a novel Continual Learning approach for NER, which requires new training material to be annotated only for the new entities. To preserve the existing knowledge previously learned by the model, we exploit the Knowledge Distillation (KD) framework, where the existing NER model acts as the teacher for a new NER model (i.e., the student), which learns the new entity by using the new training material and retains knowledge of old entities by imitating the teacher's outputs on this new training set. Our experiments show that this approach allows the student model to ``progressively'' learn to identify new entities without forgetting the previously learned ones. We also present a comparison with multiple strong baselines to demonstrate that our approach is superior for continually updating an NER model.

Traceability for some people, is merely a tool to keep a history over something important that happened in the past. For others, is has no added value to their actual processes or products. In fact, it is becoming more and more valued. Traceability is still a vast area of research and an undiscovered field that if it is well used and managed, can provide a set of critical information or lead to something bigger. Many researches are still working to enhance its use and its integration by providing solutions to help users better manage and control their different elements (products, source code, documents, requirements, specifications, etc.). Nowadays, it is used in almost all domains as it can provide reliable information and helps improve efficiency and productivity. In this paper, we first present the state of the art on traceability and its use, through several examples. Then we provide a list of major techniques used in this field and propose our own traceability definition models.

No abstract

No abstract

No abstract