the present paper focused on the sociocultural explanations of rhetorical differences between english and persian and was based on the contrastive genre analysis of applied linguistics research article abstracts in these two languages. the evolutionary nature of research article abstracts was also investigated from 1985 to 2005, in three stages, with a time interval of 10 years. seventy eight r...

Most Web pages contain temporal information. However, most of previous studies only consider the update time of Web pages rather than fully exploit different temporal features in Web. In this paper, we propose a novel approach to fusing different temporal features in Web pages to build an efficient index structure for temporal-textual Web search. Specially, we focus on update time and content t...

In this paper, we explore ways of improving an inference rule collection and its application to the task of recognizing textual entailment. For this purpose, we start with an automatically acquired collection and we propose methods to refine it and obtain more rules using a hand-crafted lexical resource. Following this, we derive a dependency-based structure representation from texts, which aim...

In this work a proposal for automatic textual segmentation is described. The proposal uses the output of an automatic syntactic analyzer – Parser Palavras – to create textual segmentation. Parse trees are used to infer text segments and a dependency tree of the identified segments. The main contribution of this work is the use of the syntactic structure as source for the automatic segmentation ...

In this thesis, we present a novel approach for modeling textual entailment using lexicalsemantic information on the level of predicate-argument structure. To this end, we adopt information provided by the Berkeley FrameNet repository and embed it into an implemented end-to-end system. The two main goals of this thesis are the following: (i) to provide an analysis of the potential contribution ...

XML (Extensible Markup Language) is a textual markup language designed for the creation of self-describing documents. Such documents contain textual data combined with structural information describing the structure of the textual data. Currently, products and approaches for document-oriented application domains focus mainly on the textual representation when processing and analyzing documents....

我們所參與公開評測 NTCIR10 RITE-2[5]將文字蘊涵的研究分成兩種層面,首先是分兩 類(Binary Class, BC) ,任務的目標是單純判別 T1 與 T2 之間是否具有蘊涵關係。但句 子之間蘊涵關係並不能單純以有或沒有這麼簡單就區分開,NTCIR RITE 另外定義多類 (Multi Class, MC)這項任務,將句子之間的蘊涵分類為正向、雙向、矛盾、與獨立四種 關係。假設這個句子對具有蘊涵關係,但有可能兩個句子所包涵的資訊數量不同,造成 我們只能從其中一個句子推論出另一個句子的完整的意思,這樣的情況我們稱為兩個句 子間的蘊涵關係為正向蘊涵。反之兩個句子可以互相推論出另一個句子的含意,這樣的 情況我們就稱為雙向蘊涵關係。假設句子對之間沒有蘊涵關係,我們可以很合理認為兩 個句子所表達的意思不相同,但這並不完全正確的想法。可能兩個句子所包涵的資訊大 致相同只是少部份...