You Don’t Need Labeled Data for Open-Book Question Answering

Open-book question answering is a subset of question answering (QA) 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 have a yes–no–none answer and a text answer which can be short (a few words) or long (a few sentences). We present a two-step, retriever–extractor architecture in which a retriever finds the right documents and an extractor finds the answers in the retrieved documents. To test our solution, we are introducing a new dataset for open-book QA based on real customer questions on AWS technical documentation. In this paper, we conducted experiments on several information retrieval systems and extractive language models, attempting to find the yes–no–none answers and text answers in the same pass. Our custom-built extractor model is created from a pretrained language model and fine-tuned on the the Stanford Question Answering Dataset—SQuAD and Natural Questions datasets. We were able to achieve 42% F1 and 39% exact match score (EM) end-to-end with no domain-specific training.

“Коммуникационный поворот” в истории России раннего Нового времени

Simon Franklin and Katherine Bowers, eds., Information and Empire: Mechanisms of Communication in Russia, 1600–1850, Cambridge: Open Book Publishers, 2017. 444 p. ISBN 9781783743735.

Open-Book Management and Organizational Success of Deposit Money Banks in South-South, Nigeria

Organizational success is of the main drivers in achieving organizational goal and objectives as indicated in literature. Based on this evidenced the study focused the relationship between open book management and organizational success of deposit money banks in Nigeria. The study adopted quasi-experimental research design and examined the population of 200 employees with a sample size of 133 respondents in four deposit money banks in Nigeria. Questionnaire was the measure instrument for data collection and the collected data were analyzed using Spearman’s’ Rank Order Correlation Coefficient statistic. The result shows a significant relationship between the dimensions of open book management and organizational success measures of deposit money banks in Nigeria. Therefore, the study concluded that open book management affect organizational success and recommended that management should periodically make employees to know about the financial statues of the organization and to develop employees’ recognition programs and provide pay-performance programs that will stimulate employees’ performance toward achievement of organizational success.