Semantic interpretation

semantic interpretation in artificial intelligence with ambiguity and dis-ambiguity...

1. SEMENTIC INTERPRETATION - AMBIGUITY AND DISAMBIGUITY BY, VIVEK KUMAR( [email protected] ) DEPT. OF COMPUTER ENGINEERING 1

2. 2 SEMANTIC OVERVIEW Semantics means the meaning and interpretation of words, signs, and sentence structure . Semantics largely determine our reading comprehension, how we understand others, and even what decisions we make as a result of our interpretations . Semantics can also refer to the branch of study within linguistics that deals with language and how we understand meaning.

3. Semantic example: 3 Above figure explain about the interpretation of word “I saw bats”. It means someone can interpret same sentence by the two different meaning like either a cricket bat or mammal bat.

4. 4 One of the central issues with semantics is the distinction between literal meaning and figurative meaning. With literal meaning, we take concepts at face value. For example, if we said, 'Fall began with the turning of the leaves,' we would mean that the season began to change when the leaves turned colours. Figurative meaning utilizes similes and metaphors to represent meaning and convey greater emotion. For example, 'I'm as hungry as a bear' would be a simile and a comparison to show a great need for sustenance.

5. SEMANTIC INTERPRETATION semantic interpretation is the process of mapping a syntactically analyzed text of natural language to a representation of its meaning. it's the process of determining what a user said versus what they meant. What the user meant is the semantic interpretation. The goal of interpretation is binding the user expression to concept, or something the system can understand. 5

6. 6 The semantic representation of an object is obtained from the semantic interpretation of its components . The semantic interpretation process must be based in a theory, not in an "ad-hoc " process. This theory must support: - lexical and syntactic ambiguity - complex phenomena: negation, quantification, inferences, etc . An interface mechanism between sintax and semantic must be defined .

7. For example Let's say you have a call router, a customer calls in and asks to speak with technical service. A second customer calls in and asks to speak with technical support. A third customer simply asks for support. All three callers meant exactly the same thing, they are trying to get to the exact same place. They all wanted technical support, but they used three different phrases to get across the same meaning. As humans we can do semantic interpretation very well, computers require more explicit input. Semantic interpretation will allow you take all three of those expression and return a single result that can be predictable and useful by computer code. 7

8. 8 USE OF SEMANTIC INTERPRETATION semantic interpretation is used to control and format the kind of output from the speech engine to some application. Let's say you have a prompt that asks the caller for a PIN (a series of digits), so the caller responds, "1, 2, 3, 4." Well, the speech engine understands words and not really numbers. It sees number as words and not digits. So it will return to you the words "one, two, three," and the word " four." You could probably perform transformations with the application so that you could replace the word "one" with a digit.

9. 9 However, using semantic interpretation you can go ahead and turn those words into numbers before it even reaches the application, which is quite handy because your application is going to want to work with just digits

10. AMBIGUITY Ambi g u i ty ca n b e d e fi n ed a s a wor d , phras e o r s e nt e n c e th a t has more than one meaning or interpretation . In some cases, listener are consciously aware of ambiguity in an expression. Ambiguity is a type of uncertainty of meaning in which several interpretations are possible. The concept of ambiguity is generally contrasted with lack of definition. Context may play a role in resolving ambiguity . 10

11. For Example: 11 Light (not very dark) Light (not very heavy)

12. Types of ambiguity Structural ambiguity Lexical ambiguity Structural ambiguity: Structural ambiguity refers to the situation in which a sentence may have different meanings because the words of a sentence are related to each other in various ways, even though each word is clear . syntactic ambiguity is the presence of two or more possible meanings within a single sentence or sequence of words. Also called structural ambiguity or grammatical ambiguity . 12

13. For Example: Small boys and girls are playing hide and seek. Explanation can show in the first sentence two ideas : Small boys are playing with young girls. Small boys and all girls are playing. Distinct underlying interpretations that have to be represented differently in deep structure is called Structural Ambiguity. 13

14. LEXICAL AMBIGUITY If a word has more than one interpretation and this same piece of information may be ambiguous in one context and unambiguous in another . It is also called semantic ambiguity. Examples : “Young” can be interpreted as young (age) or inexpert . “Bank” can also be interpreted as the slope side of a river or the financial institution. 14

15. OTHER TYPES OF AMBIGUITY Metonymy: It is a figure of speech in which one object is used to stand for another. To handle the semantics of metonymy , we need to introduce a new level of ambiguity . For semantic interpretation of every phrase in the sentence, we provide two objects : one for literal reference and one for metonymic references. Then establish relation between the two references . Metaphor: Another Figure Of Speech , a phrase with one literal meaning is used to suggest a different meaning by way of analogy. 15

16. DISAMBIGUATION MODELS To do Disambiguation properly, we need to combine four models : The World Model: likelihood that a proposition occurs in the world. Speaker : “I am Dead.” The above sentence could mean that “I am in big trouble.” rather than “My life ended, and yet I can still a talk”. B. The Mental World: likelihood that the speaker forms the intention of communicating a certain fact to the hearer . In other words, this approach combines models of what the speaker believes, what the speaker believes the hearer believes , and so on. 16

17. DISAMBIGUATION MODELS C . The Language model: likelihood that a certain strings of words will be chosen, given that the speaker has the intention of communicating a certain fact. D. The Acoustic Model: likelihood that a particular sequence of sounds will be generated , given that the speaker has chosen a given string if words(speech recognition). 17

18. References https:// en.wikipedia.org/wiki/Syntactic_ambiguity https:// www.google.co.in/search?safe=active&client=firefox-b-ab&dcr=0&q=types+of+ambiguity&sa=X&ved=0ahUKEwie2_Hxp63XAhUIwI8KHTauBiEQ1QIIiQEoAw&biw=1366&bih=635 http:// citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.307.1757&rep=rep1&type=pdf Artificial intelligence – A modern approach by stuart Russell,peter Norving . 18

19. Thank You... 19