Related papers: ESG Accountability Made Easy: DocQA at Your Servic…
Visually-situated languages such as charts and plots are omnipresent in real-world documents. These graphical depictions are human-readable and are often analyzed in visually-rich documents to address a variety of questions that necessitate…
State-of-the-art extractive question-answering models achieve superhuman performances on the SQuAD benchmark. Yet, they are unreasonably heavy and need expensive GPU computing to answer questions in a reasonable time. Thus, they cannot be…
Deep reading models for question-answering have demonstrated promising performance over the last couple of years. However current systems tend to learn how to cleverly extract a span of the source document, based on its similarity with the…
Extracting key information from documents represents a large portion of business workloads and therefore offers a high potential for efficiency improvements and process automation. With recent advances in Deep Learning, a plethora of Deep…
We propose DailyQA, an automatically updated dynamic dataset that updates questions weekly and contains answers to questions on any given date. DailyQA utilizes daily updates from Wikipedia revision logs to implement a fully automated…
Retrieval-Augmented Generation (RAG) is a cornerstone of modern question answering (QA) systems, enabling grounded answers based on external knowledge. Although recent progress has been driven by open-domain datasets, enterprise QA systems…
Discrete reasoning over table-text documents (e.g., financial reports) gains increasing attention in recent two years. Existing works mostly simplify this challenge by manually selecting and transforming document pages to structured tables…
A fundamental trade-off between effectiveness and efficiency needs to be balanced when designing an online question answering system. Effectiveness comes from sophisticated functions such as extractive machine reading comprehension (MRC),…
We present NewsQA, a challenging machine comprehension dataset of over 100,000 human-generated question-answer pairs. Crowdworkers supply questions and answers based on a set of over 10,000 news articles from CNN, with answers consisting of…
Current tasks and methods in Document Understanding aims to process documents as single elements. However, documents are usually organized in collections (historical records, purchase invoices), that provide context useful for their…
Machine reading is a fundamental task for testing the capability of natural language understanding, which is closely related to human cognition in many aspects. With the rising of deep learning techniques, algorithmic models rival human…
AI systems' ability to explain their reasoning is critical to their utility and trustworthiness. Deep neural networks have enabled significant progress on many challenging problems such as visual question answering (VQA). However, most of…
Accessing suitable datasets is critical for research and development in recommender systems. However, finding datasets that match specific recommendation task or domains remains a challenge due to scattered sources and inconsistent…
In this paper we describe a web search agent, called Global Search Agent (hereafter GSA for short). GSA integrates and enhances several search techniques in order to achieve significant improvements in the user-perceived quality of…
We present GPQA, a challenging dataset of 448 multiple-choice questions written by domain experts in biology, physics, and chemistry. We ensure that the questions are high-quality and extremely difficult: experts who have or are pursuing…
The large volumes of structured data currently available, from Web tables to open-data portals and enterprise data, open up new opportunities for progress in answering many important scientific, societal, and business questions. However,…
Climate decision making is constrained by the complexity and inaccessibility of key information within lengthy, technical, and multi-lingual documents. Generative AI technologies offer a promising route for improving the accessibility of…
Spoken question answering (SQA) is a challenging task that requires the machine to fully understand the complex spoken documents. Automatic speech recognition (ASR) plays a significant role in the development of QA systems. However, the…
This paper proposes a question-answering system that can answer questions whose supporting evidence is spread over multiple (potentially long) documents. The system, called Visconde, uses a three-step pipeline to perform the task:…
Document Understanding is a foundational AI capability with broad applications, and Document Question Answering (DocQA) is a key evaluation task. Traditional methods convert the document into text for processing by Large Language Models…