Web contains a vast amount of data, which are accumulated, studied, and utilized by a huge
number of users on a daily basis. A substantial amount of data on the Web is available in an …

To respond correctly to a free form factual question given a large collection of text data, one
needs to understand the question to a level that allows determining some of the constraints …

A knowledge graph (KG) has nodes and edges representing entities and relations. KGs are
central to search and question answering (QA), yet research on deep/neural representation …

(哈尔滨工业大学信息检索研究室, 黑龙江哈尔滨150001) 摘要: 问题分类是问答系统中重要的
组成部分, 问题分类结果的好坏直接影响问答系统的质量. 本文提出了一种用于问题分类的特征 …

In this paper we explore some of the most important areas of advanced information retrieval.
In particular, we look at cross-lingual information retrieval, multimedia information retrieval …

In statistical question classification, semi-supervised learning that can exploit the abundant
unlabeled samples has received substantial attention in recent years. In this paper, a novel …

问答系统应能用准确, 简洁的答案回答用户用自然语言提出的问题. 问题分类是问答系统所要
处理的第一步, 分类结果的**确率直接影响后续工作的进行. 本文提出了一种使用知网作为语义 …

Support vector machine have been widely used in classification tasks, however, the
structure of the question is ignored while using the standard kernel function in the question …

This paper discusses the query-based multidocument summarization techniques
implemented by the Hong Kong Polytechnic University at DUC 2005. The summarization …

Current IDEs excel at text manipulation, but offer little support for sketching and capturing
informal visual artifacts that developers create during their work on the code base. Such …