The conventional semantic text-similarity methods requires high amount of trained labeled
data and also human interventions. Generally, it neglects the contextual-information and …

One of the most major and essential tasks in natural language processing is machine
translation that is now highly dependent upon multilingual parallel corpora. Through this …

In this paper we propose a summarization approach, nicknamed AZOM, that combines
statistical and conceptual property of text and in regards of document structure, extracts the …

The importance of text summarization grows rapidly as the amount of information increases
exponentially. In this paper, we present new method for Persian Text Summarization based …

In recent years, learning ranking function for information retrieval has drawn the attentions of
the researchers from information retrieval and machine learning community. In existing …

Aiming at the problem that there are a great deal of redundant security events in current
network security systems, this article proposed a security event correlation algorithm based …

There exist noisy, unparallel sentences in parallel web pages. Web page structure is
subjected to some limitation for sentences alignment task for web page text. The most …

As the amount of information and the number of queries has been increasing today,
indexing is a good solution to fight with the inherent complexity of text retrieval and …

In recent years, the algorithms of learning to rank have been proposed by researchers.
However, in information retrieval, instances of ranks are imbalanced. After the instances of …

The traditional image retrieval approach allows users to create, share and comment media
on a large scale. The large scale data not only promote users in sharing and organizing …