IJCNLP 2011 Proceedings of the KRAQ 11 Workshop : Knowledge and Reasoning for Answering Questions
نویسنده
چکیده
In this paper, we present the KOMODO system which is designed to provide tips (advice and warnings) on the way to realize a task from user queries. Information is extracted from web services. We present the different steps of the system: web page selection, ranking and cleaning, extraction of warnings and advice, relevance analysis and contextualization, and production of a response. The different language processing steps are presented together with an evaluation of the results. The system is fully tested and a demonstration will be made if possible during the presentation.
منابع مشابه
Towards deep reasoning with respect to natural language text in scientific domains
In this paper we take some initial steps towards deep reasoning with respect to natural language text in scientific domains. In particular we consider answering Why and How questions with respect to a high school Biology text. In comparison to other kinds of questions, Why and How questions (the later referred to as procedural questions by some) have been less explored in the Question Answering...
متن کاملThe effect of short-term workshop on improving clinical reasoning skill of medical students
Background: Clinical reasoning process leads clinician to get purposeful steps from signs and symptoms toward diagnosis and treatment. This research intends to investigate the effect of teaching clinical reasoning on problem-solving skills of medical students. Methods: This research is a semi-experimental study. Nineteen Medical student of the pediatric ward as case group participated...
متن کاملIntegrating Subject, Type, and Property Identification for Simple Question Answering over Knowledge Base
This paper presents an approach to identify subject, type and property from knowledge base for answering simple questions. We propose new features to rank entity candidates in KB. Besides, we split a relation in KB into type and property. Each of them is modeled by a bi-directional LSTM. Experimental results show that our model achieves the state-of-the-art performance on the SimpleQuestions da...
متن کاملارزیابی منابع اطلاعاتی پزشکی مبتنی بر شواهد براساس میزان پاسخدهی به پرسشهای بالینی
Introduction: This study was to identify the best accessible electronic information resources for finding answers to clinical questions in Iranian National Medical Digital Library. Methods: 20 clinical questions were randomly selected from four areas: prevention and treatment, diagnosis, etiology and prognosis from American National Library of Medicine (NLM). The keywords were searched in info...
متن کاملThe Effect of Bayesian Reasoning Training on the Results of Clinical Reasoning Tests of Interns
Introduction: Clinical reasoning includes a range of thinking about clinical medicine at all stages of patient evaluation. Bayesian theory can be used to refute or confirm differential diagnoses in the clinical reasoning process. In this way, by learning the basic mathematical language of probability in medicine, we can change our beliefs according to new evidence. The aim of this study is to i...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2011