In the previous session, we had mentioned that there are three broad levels of syntactic processing:
- Part-of-speech tagging.
- Constituency parsing.
- Dependency parsing.
You have studied POS tagging in detail, though that is not enough for understanding the complex grammatical structures and ambiguities in sentences which most human languages comprise of.
Therefore, we need to learn techniques which can help us understand the grammatical structures of complex sentences. Constituency parsing and dependency parsing can help us achieve that.
In This Session
In this session, you’ll study parsing techniques and algorithms to understand the grammatical structure of sentences. In constituency parsing, you will learn to parse complex sentences using what are called grammar rules. You’ll also study an alternative parsing technique called dependency parsing.
Topics covered in this session include:
Constituency Parsing.
- Context-Free Grammar (CFG).
- Bottom-up and top-down parsing algorithms.
- Probabilistic CFG, or PCFG.
Dependency Parsing
- Fixed and free word order languages.
- Elements of dependency grammar.
- Overview of dependency parsing algorithms.
Note that dependency parsing is a recent topic in the field of NLP whose study involves a fairly deep understanding of the English grammar and parsing algorithms, which is not possible to cover in the span of this course. However, in this session, we’ll cover the basics of dependency parsing techniques which should enable you to consume more sophisticated texts on the topic and introduce you to such additional resources for further study.
People you will hear from in this session:
Subject Matter Expert
Professor and Dean, R&D, IIIT- B
The International Institute of Information Technology, Bangalore, also known as IIIT-B, is one of India’s foremost graduate schools. Through its Integrated M.Tech., M.Tech., M.S. (Research) and PhD programs in the IT space, it focuses equally on innovation and education.