Week 12 UAS

Question 1

NLP problem can be divided into two tasks?

Answer 1

1. Processing written text, using lexical, syntactic and semantic knowledge of the language as well as the required real world information.
2. Processing spoken language, using all the information needed above plus additional knowledge about phonology as well as enough added information to handle the further ambiguities that arise in speech.

Question 2

5 Steps in NLP?

Answer 2

1. Morphological Analysis:
   Individual words are analyzed into their components and nonword tokens such as punctuation are separated from the words.
2. Syntactic Analysis:
   Linear sequences of words are transformed into structures that show how the words relate to each other.
3. Semantic Analysis:
   The structures created by the syntactic analyzer are assigned meanings.
4. Discourse integration:
   The meaning of an individual sentence may depend on the sentences that precede it and may influence the meanings of the sentences that follow it.
5. Pragmatic Analysis:
   The structure representing what was said is reinterpreted to determine what was actually meant.

Question 3

Syntactic Processing: Almost all the systems that are actually used have two main components:

Answer 3

1. A declarative representation, called a grammar, of the syntactic facts about the language.
2. A procedure, called parser, that compares the grammar against input sentences to produce parsed structures.

Question 4

Real human languages provide many problems for NLP

Answer 4

1. ambiguity
2. anaphora
3. indexicality
4. vagueness
5. discourse structure
6. metonymy
7. metaphor
8. noncompositionality

Question 5

3 types of understanding as constraint satisfaction?

Answer 5

1. An Obscuring Edge A boundary between objects, or between objects and the background
2. A Concave Edge An edge between two faces that form an acute angle when viewed from outside the object
3. A Convex Edge An edge between two faces that form an obtuse angle when viewed from outside the object

Question 6

Various cues in the image that enable one to obtain 3D about scene?

Answer 6

motion, stereopsis, texture, shading, and contour.

Question 7

All things that should be prepared or planned before we can successfully build a learning-based intelligent systems application?

Answer 7

1. which components of the performance element are to be learned
2. what feedback is available to learn these components
3. what representation is used for the components

Question 8

3-layer architecture?

Answer 8

1. the reactive layer provides low-level control to the robot. It is characterized by a tight - action loop. Its decision cycle is often on the order of milliseconds.
2. the executive layer (sequencing layer) serves as the glue between the reactive layer and the deliberative layer. It accepts directives by the deliberative layer and sequences them for the reactive layer.
3. the deliberative layer generates global solutions to complex tasks using planning.