File Information
File: 05-lr/acl_arc_1_sum/cleansed_text/xml_by_section/intro/04/n04-4014_intro.xml
Size: 1,906 bytes
Last Modified: 2025-10-06 14:02:19
<?xml version="1.0" standalone="yes"?> <Paper uid="N04-4014"> <Title>HITIQA: A Data Driven Approach to Interactive Analytical Question Answering</Title> <Section position="2" start_page="0" end_page="0" type="intro"> <SectionTitle> 1 Introduction </SectionTitle> <Paragraph position="0"> Our objective in HITIQA is to allow the user to submit exploratory, analytical questions, such as &quot;What has been Russia's reaction to U.S. bombing of Kosovo?&quot; The distinguishing property of such questions is that one cannot generally anticipate what might constitute the answer. While certain types of things may be expected (e.g., diplomatic statements), the answer is heavily conditioned by what information is in fact available on the topic. From a practical viewpoint, analytical questions are often underspecified, thus casting a broad net on a space of possible answers. Questions posed by professional analysts are aimed to probe the available data along certain dimensions. The results of these probes determine follow up questions, if necessary. Furthermore, at any stage clarifications may be needed to adjust the scope and intent of each question. Figure 1a shows a fragment of an analytical session with HITIQA; please note that these questions are not aimed at factoids, despite appearances. HITIQA project is part of the ARDA AQUAINT program that aims to make significant advances in state of the art of automated question answering. null User: What is the history of the nuclear arms program between Russia and Iraq? HITIQA: [responses and clarifications] User: Who financed the nuclear arms program in Iraq? HITIQA:...</Paragraph> <Paragraph position="1"> User: Has Iraq been able to import uranium? HITIQA:...</Paragraph> <Paragraph position="2"> User: What type of debt does exist between Iraq and Russia? FIGURE 1a: A fragment of analytic session</Paragraph> </Section> class="xml-element"></Paper>