Parameter-Efficient Abstractive Question Answering over Tables or Text
Vaishali Pal, Evangelos Kanoulas, Maarten de Rijke · 2022
A long-term ambition of information seeking question answering (QA) systems is to reason over multi-modal contexts and generate natural answers to user queries.Today, memory intensive pre-trained language models are adapted to downstream tasks such as QA by fine-tuning the model on QA data in a specific modality like unstructured text or structured tables.To avoid training such memoryhungry models while utilizing a uniform architecture for each modality, parameter-efficient adapters add and train small task-specific bottleneck layers between transformer layers.In this work, we study parameter-efficient abstractive QA in encoder-decoder models over structured tabular data and unstructured textual data using only 1.5% additional parameters for each modality.We also ablate over adapter layers in both encoder and decoder modules to study the efficiency-performance trade-off and demonstrate that reducing additional trainable parameters down to 0.7%-1.0%leads to comparable results.Our models out-perform current stateof-the-art models on tabular QA datasets such as Tablesum and FeTaQA, and achieve comparable performance on a textual QA dataset such as NarrativeQA using significantly less trainable parameters than fine-tuning.