Generating Query Focused Summaries without Fine-tuning the Transformer-based Pre-trained Models
This addresses computational efficiency for NLP practitioners by offering an incremental method to reduce fine-tuning overhead in query-focused summarization.
The paper tackles the problem of high computational cost and carbon footprint from fine-tuning transformer models for query-focused summarization by proposing a Marginal Maximum Relevance (MMR)-based approach that avoids fine-tuning, showing better performance than individual pre-trained models on WCEP and Debatepedia datasets.
Fine-tuning the Natural Language Processing (NLP) models for each new data set requires higher computational time associated with increased carbon footprint and cost. However, fine-tuning helps the pre-trained models adapt to the latest data sets; what if we avoid the fine-tuning steps and attempt to generate summaries using just the pre-trained models to reduce computational time and cost. In this paper, we tried to omit the fine-tuning steps and investigate whether the Marginal Maximum Relevance (MMR)-based approach can help the pre-trained models to obtain query-focused summaries directly from a new data set that was not used to pre-train the models. First, we used topic modelling on Wikipedia Current Events Portal (WCEP) and Debatepedia datasets to generate queries for summarization tasks. Then, using MMR, we ranked the sentences of the documents according to the queries. Next, we passed the ranked sentences to seven transformer-based pre-trained models to perform the summarization tasks. Finally, we used the MMR approach again to select the query relevant sentences from the generated summaries of individual pre-trained models and constructed the final summary. As indicated by the experimental results, our MMR-based approach successfully ranked and selected the most relevant sentences as summaries and showed better performance than the individual pre-trained models.