Par4Sim -- Adaptive Paraphrasing for Text Simplification
This work addresses the problem of adaptive learning in NLP for text simplification, representing an incremental advancement by applying existing adaptive methods to a new domain.
The paper tackles the challenge of continuously improving an NLP model for text simplification without explicit supervision by developing an adaptive learning system that updates a learning-to-rank model from user usage data, resulting in performance increasing from 62.88% to 75.70% on NDCG@10 metrics.
Learning from a real-world data stream and continuously updating the model without explicit supervision is a new challenge for NLP applications with machine learning components. In this work, we have developed an adaptive learning system for text simplification, which improves the underlying learning-to-rank model from usage data, i.e. how users have employed the system for the task of simplification. Our experimental result shows that, over a period of time, the performance of the embedded paraphrase ranking model increases steadily improving from a score of 62.88% up to 75.70% based on the NDCG@10 evaluation metrics. To our knowledge, this is the first study where an NLP component is adaptively improved through usage.