Automatic Question Answering: Beyond the Factoid
Automatic Question Answering: Beyond the Factoid
复制标题
DOI：
--
复制
发表时间：
2004
期刊：
影响因子：
--
通讯作者：
Radu Soricut;Eric Brill
中科院分区：
文献类型：
--
作者：
Radu Soricut;Eric Brill
在本文中，我们描述和评估的问题回答系统，超越回答事实问题。我们专注于常见问题和答案，并建立我们的系统周围的噪声通道架构，利用一个语言模型的答案和转换模型的答案/问题的条款，从网络上收集的语料库100万个问题/答案对训练。
In this paper we describe and evaluate a Question Answering system that goes beyond answering factoid questions. We focus on FAQlike questions and answers, and build our system around a noisy-channel architecture which exploits both a language model for answers and a transformation model for answer/question terms, trained on a corpus of 1 million question/answer pairs collected from the Web.