Parameter-Efficient Abstractive Question Answering over Tables or Text

• Published in: arXiv.org
• Main Authors: Pal, Vaishali, Kanoulas, Evangelos, de Rijke, Maarten
• Format: Paper Journal Article
• Language: English
• Published: Ithaca Cornell University Library, arXiv.org 07.04.2022
• Subjects: Ablation; Adapters; Coders; Computer Science - Artificial Intelligence; Computer Science - Computation and Language; Datasets; Encoders-Decoders; Mathematical models; Parameters; Tables (data); Unstructured data
• ISSN: 2331-8422
• DOI: 10.48550/arxiv.2204.03357

A long-term ambition of information seeking 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 memory-hungry models while utilizing a uniform architecture for each modality, parameter-efficient adapters add and train small task-specific bottle-neck 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 state-of-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.