Word Sense Disambiguation (WSD)Series-1
Natural Language Problems & Solutions …
There are words in Natural languages which have different meaning for different context but they are spelled same. Those words are called polysemous words. Word sense disambiguation (WSD) is the solution to the problem.
Word Sense Disambiguation is a task of finding the correct sense of the words and automatically assigning its correct sense to the words which are polysemous in a particular context.
Word Sense Disambiguation (WSD) is an important but challenging technique in the area of natural language processing (NLP).
Human beings are blessed with the learning power. They can easily find out what is the correct meaning of a word in a context. But for computer it is a difficult task. So, we need to develop an automatic system which can perform like humans do i.e. the system which can find out the correct meaning of the word in particular context and automatically assign the optimal sense to the target word.
Common approaches to solve WSD
Now we will see various approaches used for WSD and classifies existing WSD algorithms according to their techniques.
Machine learning techniques
A classifier is used to learn features and assign senses to unseen examples
In this approach initial input is the word to be disambiguated called target word and the text in which is embedded called as context.
In this approach features are themselves served by the words
Supervised Techniques
It uses ML techniques for inducing a classifier from manually sense-annotated data sets. Usually, the classifier is concerned with a single word and performs a classification task in order to assign the appropriate sense to each instance of that word
Examples of supervised techniques are decision lists, Decision Tree, Naïve Bayes , Nural Networks
Un-Supervised Techniques
It don’t need hand labeled knowledge of sense information in large scale resources for the disambiguation
Examples are context clustering and co-occurrence graphs
semi-supervised techniques
Here, the information is present like in supervised but might be less information is given.Here only critic information is available,not the exact information.
For example, School-Uniform, School-shoes are the words with semantic relationship. In this approach improper word senses are omitted and only those senses are selected which have harmony with common sense rules. The basic idea behind this approach is to count how many times this kind of word pair occurs in the corpus with syntactic relation. From this count, senses of words will be identified. There are other methods, which can find this kind of relation among words using conditional probability.
Dictionary Based approaches
Knowledge based approach based on knowledge resources of machine readable dictionaries in form of corpus, WorldNet etc
Overlap Based Approaches
This approach calls for the requirement of machine readable dictionary (MDR). It includes determination of the different fea-tures of the senses of words which are ambiguous along with features of the words in the context.
Conclusion
Different approaches available in word sense disambiguation with primarily focusing on the Machine Learning Approaches and Dictionary based approaches,knowledge based. with different experiments I observed supervised approach is found to perform better but one of its dis-advantage is the requirement of a large corpora with-out which training is impossible which can be over-came in unsupervised approach as it does not rely on any such large scale resource for the disambiguation.
Knowledge based approach on the other hand makes use of knowledge sources to decide upon the senses of words in a particular context provided machine readable knowledge base is available to apply.
will meet with next blog with solution…
Thanks for the reading and Besides, leave a few claps if you found this text helpful!!!
