Textual Unit
(Redirected from Text Item)
Jump to navigation
Jump to search
A Textual Unit is a Linguistic Unit that can be combined with others o form a Textual Structure.
- Example(s):
- Elementary Textual Units,
- ...
- …
- Counter-Example(s):
- See: Text Document, Unrestricted Text, Open Information Extraction, Tuple, Cohesion Trees, Text Representation, Feature Vector, Semantic Space Measure, Contextual Representation.
References
2002
- (Mehler, 2002) ⇒ Alexander Mehler (2002). "Hierarchical Orderings of Textual Units". In: Proceeding of the 19th International Conference on Computational Linguistics (COLING 2002).
- QUOTE: Text representation is a central task for any approach to automatic learning from texts. It requires a format which allows to interrelate texts even if they do not share content words, but deal with similar topics. Furthermore, measuring text similarities raises the question of how to organize the resulting clusters. This paper presents cohesion trees (CT) as a data structure for the perspective, hierarchical organization of text corpora. CTs operate on alternative text representation models taking lexical organization, quantitative text characteristics, and text structure into account. It is shown that CTs realize text linkages which are lexically more homogeneous than those produced by minimal spanning trees.
1997
- (Marcu, 1997) ⇒ Daniel Marcu. (1997). “Rhetorical Parsing, Summarization, and Generation of Natural Language Texts". PhD Thesis. University of Toronto.
- QUOTE: In formalizing the structure of unrestricted texts (in chapter 2), I first distill the features that are common to previous approaches and show that most discourse theories acknowledge that text can be sequenced into elementary units; that discourse relations of various natures hold between textual units of various sizes; that some textual units are more essential to the writer's purpose than others; and that trees are a good approximation of the abstract structure of text.