TSUNAMI: Simultaneous understanding, answering, and memory interaction for questions
نویسندگان
چکیده
منابع مشابه
Question-Answering via Enhanced Understanding of Questions
We describe a machine learning centered approach to developing an open domain question answering system. The system was developed in the summer of 2002, building upon several existing machine learning based NLP modules developed within a unified framework. Both queries and data were pre-processed and augmented with pos tagging, shallow parsing information, and some level of semantic categorizat...
متن کاملAnswering Questions about Questions: A Persuasion Knowledge Perspective for Understanding the Effects of Rhetorical Questions
Past research is not clear on the process by which rhetorical questions influence persuasion (i.e., increased focus on message arguments vs. on the persuasion agent). Based on recent theories of persuasion knowledge and rhetorical figures in advertising, our model delineates conditions under which rhetoricals are likely to enhance argument elaboration (low salience of the rhetorical) and those ...
متن کاملAutomated Modeling for Answering Prediction Questions: Exploiting Interaction Paths*
This paper presents an algorithm for constructing differential equation models to answer prediction questions. A prediction question poses a hypothetical scenario and asks for the resulting behaviors of specific real-valued state variables (“quantities of interest”). A model for such a question should include only those aspects of the scenario relevant to the quantities of interest. Furthermore...
متن کاملTowards Understanding and Answering Multi-Sentence Recommendation Questions on Tourism
We introduce the first system towards the novel task of answering complex multisentence recommendation questions in the tourism domain. Our solution uses a pipeline of two modules: question understanding and answering. For question understanding, we define an SQL-like query language that captures the semantic intent of a question; it supports operators like subset, negation, preference and simi...
متن کاملExploiting Diversity for Answering Questions
We describe initial experiments in combining the output of question answering systems using data from the 2002 TREC Question Answering task. We explore several distance-based combining methods, as well as a number of distance metrics involving both word and character ngrams.
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Cognitive Science
سال: 1994
ISSN: 0364-0213
DOI: 10.1016/0364-0213(94)90020-5