Zero-Shot Open-Book Question Answering

Abstract

Open book question answering is a subset of question answering tasks where the system aims to find answers in a given set of documents (open-book) and common knowledge about a topic. This article proposes a solution for answering natural language questions from a corpus of Amazon Web Services (AWS) technical documents with no domain-specific labeled data (zero-shot). These questions can have yes-no-none answers, short answers, long answers, or any combination of the above. This solution comprises a two-step architecture in which a retriever finds the right document and an extractor finds the answers in the retrieved document. We are introducing a new test dataset for open-book QA based on real customer questions on AWS technical documentation. After experimenting with several information retrieval systems and extractor models based on extractive language models, the solution attempts to find the yes-no-none answers and text answers in the same pass. The model is trained on the The Stanford Question Answering Dataset - SQuAD (Rajpurkaret al., 2016) and Natural Questions (Kwiatkowski et al., 2019) datasets. We were able to achieve 49% F1 and 39% exact match score (EM) end-to-end with no domain-specific training.

References in corpus (10)

• Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
• Language Models are Few-Shot Learners
• Bidirectional Attention Flow for Machine Comprehension
• ALBERT: A Lite BERT for Self-supervised Learning of Language Representations
• SQuAD: 100,000+ Questions for Machine Comprehension of Text
• Dynamic Memory Networks for Visual and Textual Question Answering
• RACE: Large-scale ReAding Comprehension Dataset From Examinations
• QuAC : Question Answering in Context
• QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering
• Careful Selection of Knowledge to solve Open Book Question Answering