Processing Written English
-
Upload
ruel-montefolka -
Category
Education
-
view
189 -
download
0
Transcript of Processing Written English
![Page 1: Processing Written English](https://reader036.fdocuments.net/reader036/viewer/2022062607/58efb8081a28ab86188b457d/html5/thumbnails/1.jpg)
Processing of Written Language
![Page 2: Processing Written English](https://reader036.fdocuments.net/reader036/viewer/2022062607/58efb8081a28ab86188b457d/html5/thumbnails/2.jpg)
Objectives:At the end of the lesson we would be able to;
1. understand the importance of the written
language in the 21st century education and its
meaning,
2. appreciate the valuable factors involve in
processing written language.
![Page 3: Processing Written English](https://reader036.fdocuments.net/reader036/viewer/2022062607/58efb8081a28ab86188b457d/html5/thumbnails/3.jpg)
What is written language?
the representation of a language by means
of a writing system. Written language is an
invention in that it must be taught to
children; children will pick up spoken
language (oral or sign) by exposure
without being specifically taught.
![Page 4: Processing Written English](https://reader036.fdocuments.net/reader036/viewer/2022062607/58efb8081a28ab86188b457d/html5/thumbnails/4.jpg)
Processing of Written Language
One of the most difficult topics is NLP (Natural Language Processing) : removal of the language barrier between people. This involves communicating with application programs or expert systems in the most natural and efficient format. Pattern recognition in speech and visual scene analysis are therefore significant. Success in natural language understanding has been slow in coming and achieved at great cost and effort.
![Page 5: Processing Written English](https://reader036.fdocuments.net/reader036/viewer/2022062607/58efb8081a28ab86188b457d/html5/thumbnails/5.jpg)
The goal of natural language translation was
one of the first attempted by Artificial
Intelligence (AI) researchers, and failure to
reach it proved to be one of AI's greatest
disappointments. However, analysis of past
failures allowed progress has been made to
generalise this "translation" machine.
![Page 6: Processing Written English](https://reader036.fdocuments.net/reader036/viewer/2022062607/58efb8081a28ab86188b457d/html5/thumbnails/6.jpg)
Ways of Communication of LanguagesThe majority of human linguistic
communication occurs as speech. Written language was only a recent invention and plays a less central role. However, processing written language (assuming an unambiguous representation) is easier than processing speech in general. For example, building a program that understands speech requires all facilities of a written language understand as well as enough knowledge to handle noise and ambiguities of audio signal.
![Page 7: Processing Written English](https://reader036.fdocuments.net/reader036/viewer/2022062607/58efb8081a28ab86188b457d/html5/thumbnails/7.jpg)
Thus it is useful to split the problem into two subtasks:
1. Processing written text using;
a. Syntacticb. Lexicalc. Semantic knowledge of language
2. Processing spoken language using; all information needed above, and additional knowledge about phonology.
![Page 8: Processing Written English](https://reader036.fdocuments.net/reader036/viewer/2022062607/58efb8081a28ab86188b457d/html5/thumbnails/8.jpg)
Steps in the Process
One pitfall in processing language is that it is tempting to define the language simply as a set of strings, without reference to understanding the context. However, in order to increase realism and accuracy, we must represent the language as a pair: (source language, target representation). The target representation would be chosen relevant to the situation. Hence it is possible to depict this as a mapping from the piece of language to some representation.
![Page 9: Processing Written English](https://reader036.fdocuments.net/reader036/viewer/2022062607/58efb8081a28ab86188b457d/html5/thumbnails/9.jpg)
In overview, to achieve this we need to define precisely what the underlying task and target representation would look like.
1. Morphological Analysisa. Singleton words are analysed into their respective componentsb. Non-word tokens (e.g. punctuation) are categorised separately.
![Page 10: Processing Written English](https://reader036.fdocuments.net/reader036/viewer/2022062607/58efb8081a28ab86188b457d/html5/thumbnails/10.jpg)
![Page 11: Processing Written English](https://reader036.fdocuments.net/reader036/viewer/2022062607/58efb8081a28ab86188b457d/html5/thumbnails/11.jpg)
2. Syntactic Analysis
a. Structure holds linear sequences of related words
b. Word sequence is rejected if it violates the language rules for how words may be combined For example, an English analyser would reject: "Girl the walk computer do."
![Page 12: Processing Written English](https://reader036.fdocuments.net/reader036/viewer/2022062607/58efb8081a28ab86188b457d/html5/thumbnails/12.jpg)
![Page 13: Processing Written English](https://reader036.fdocuments.net/reader036/viewer/2022062607/58efb8081a28ab86188b457d/html5/thumbnails/13.jpg)
![Page 14: Processing Written English](https://reader036.fdocuments.net/reader036/viewer/2022062607/58efb8081a28ab86188b457d/html5/thumbnails/14.jpg)
3. Semantic Analysis
a. Structures created by syntactic analyser are
assigned meanings
b. Mapping exists between syntactic structures
and objects in task domain.
c. Structures with no mappings may be
rejected (semantically anomalous). For
example, the sentence: "Colorless green
ideas sleep furiously" [Chomsky, 1957]
would be rejected
![Page 15: Processing Written English](https://reader036.fdocuments.net/reader036/viewer/2022062607/58efb8081a28ab86188b457d/html5/thumbnails/15.jpg)
![Page 16: Processing Written English](https://reader036.fdocuments.net/reader036/viewer/2022062607/58efb8081a28ab86188b457d/html5/thumbnails/16.jpg)
4. Discourse Integration a. Meaning of an individual sentence
could influence other sentences that precede or follow it.
For example, the word "it" in the sentence: "George needed it" depends on the preceding context; while the word "George" could influence the meaning of later sentences, such as "He always laughs".
![Page 17: Processing Written English](https://reader036.fdocuments.net/reader036/viewer/2022062607/58efb8081a28ab86188b457d/html5/thumbnails/17.jpg)
5. Pragmatic Analysis
a. Structure representing what was said is interpreted to determine what is required to be done.
b. Application of a set of rules that characterise co-operative dialogues.
c. Translation from knowledge-based representation to a command executed by the system.
![Page 18: Processing Written English](https://reader036.fdocuments.net/reader036/viewer/2022062607/58efb8081a28ab86188b457d/html5/thumbnails/18.jpg)
![Page 19: Processing Written English](https://reader036.fdocuments.net/reader036/viewer/2022062607/58efb8081a28ab86188b457d/html5/thumbnails/19.jpg)
Complete separation of these phases is difficult. These steps all interact in some way, and can be processed sequentially or in parallel. However, if there is dependence from one phase to another, it is critical to process in an order which satisfies the overall performance.
![Page 20: Processing Written English](https://reader036.fdocuments.net/reader036/viewer/2022062607/58efb8081a28ab86188b457d/html5/thumbnails/20.jpg)
Reference:
http://www.ling.fju.edu.tw/hearing/Processing
%20of%20Written%20Language.htm
https://www.google.com.ph/search?
q=semantics+meaning&biw=1318&bih=608&s
ource=lnms&tbm=isch&sa=X&ved=0CAYQ_A
UoAWoVChMIybzJhYWPyAIVjI6OCh1f1wdz