Knowledge Graph
Introduction to Semantic Processing
Welcome to this module ‘Semantic Processing’.
In one of the previous module, Syntactic Processing you have learnt:
- PoS tagging and HMM model
- Constituency and Dependency parsing
- Name Entity Recognition (NER)
- Custom NER and Conditional Random Fields (CRF)
- Application of each topic in Python using Spacy library
What is the need for semantic processing? In the next video, Jaidev will answer this question.
Syntactic processing involved the study of grammar to understand the meaning of sentences. However, there is no single encompassing rule book that defines grammar because language is always evolving. On the other hand, the text data that is generated is mostly grammatically incorrect.
However, we do not rely on grammar to understand the language. Remember when you were a child, you had no idea about grammar but still could understand the language easily.
Example: ‘I is a data scientist’. Although this is grammatically incorrect, we can understand it perfectly.
In this module ‘Semantic Processing’, you will learn about techniques and algorithms to infer the meaning of a given piece of text.
Semantic processing is probably the most challenging area in the field of NLP partly because the concept of ‘meaning’ itself is quite wide and because it is difficult to make machines understand the text the same way as we do–inferring the intent of a statement, the meanings of ambiguous words, dealing with synonyms, detecting sarcasm, etc.
However, we rely on the meaning and context of the words to understand the language; hence, we need semantic processing. In this module, you will learn about the following methods:
- Knowledge Graphs
- Distributional Semantics
- Topic Modelling
In this session
Now that you have an overview of the module, let us take a look at what you will be studying in this session.
We will learn the following in this session:
- Introduction to knowledge graphs
- Different types of knowledge graphs
- Applications of knowledge graphs
- WordNet
- Word sense disambiguation
Guidelines for in-module questions
The in-video and in-content questions for this module are not graded. Note that graded questions are given in a separate segment labelled ‘Graded Questions’ at the end of each session. These graded questions will adhere to the following guidelines.
| First Attempt Marks | Second Attempt Marks | |
| Questions With 2 Attempts | 10 | 5 |
| Questions With 1 Attempt | 10 | 0 |
People you will hear from in this session: