Par4Sim -- Adaptive Paraphrasing for Text Simplification

by   Seid Muhie Yimam, et al.

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 NDCG@10 evaluation metrics. To our knowledge, this is the first study where an NLP component is adaptively improved through usage.


page 4

page 5

page 9


All You Need Is Logs: Improving Code Completion by Learning from Anonymous IDE Usage Logs

Integrated Development Environments (IDE) are designed to make users mor...

Demonstrating PAR4SEM - A Semantic Writing Aid with Adaptive Paraphrasing

In this paper, we present Par4Sem, a semantic writing aid tool based on ...

NUBIA: NeUral Based Interchangeability Assessor for Text Generation

We present NUBIA, a methodology to build automatic evaluation metrics fo...

Back to Reality for Imitation Learning

Imitation learning, and robot learning in general, emerged due to breakt...

autoNLP: NLP Feature Recommendations for Text Analytics Applications

While designing machine learning based text analytics applications, ofte...

Text Assisted Insight Ranking Using Context-Aware Memory Network

Extracting valuable facts or informative summaries from multi-dimensiona...

Adaptive Sampling for Coarse Ranking

We consider the problem of active coarse ranking, where the goal is to s...