AI: Deep Learning for Semantic Similarity


In this article I discuss an research paper by (Adrian Sanborn and  Jacek Skryzalin) [1] named “Deep Learning for Semantic Similarity”.   

Aim: Given two sentences or small text fragments, are they similar? If so, how much similar or dis-similar?


The authors have proposed use of AI technique of deep learning in particular –Recurrent Neural Networks and Recursive Neural Networks. Recurrent Neural Network use the previous states in a learning mechanism. The model learned here is a non-linear function of previous states plus the new inputs. The semantic similarity model works by learning two set of words, one for each sentence. This is the learning or model building part. Deep Neural Networks require a considerable sized training data, each word here is represented by its word embedding. While in Recursive Neural Network based semantic similarity, a binary tree is fed into the model, the tree being the parse tree of the sentence.  The results obtained by the research were comprehended by authors as well in comparison to the constraints in the experimentations performed. Further, the similarity scores have been classified into six categories.

My Comments:

Semantic similarity can be used in various applications as suggested by authors as well. Once such a technique is well developed is becomes handy to compute the similarity between two comments on twitter, LinkedIn, Facebook or any social media platform. It can be used as a statistics called “statistics for comments” and can be helpful for both social media businesses and individuals too, especially those who gets lot of comments and want to get statistics of their comments, not just number of likes and dislikes. 


[1] Sanborn, A., & Skryzalin, J. (2015). Deep learning for semantic similarity. CS224d: Deep Learning for Natural Language Processing Stanford, CA, USA: Stanford University.

Published by Nidhika

I have an eager research-based approach to solve problems in the various areas using my expertise in Artificial Intelligence, Computer Science and Mathematics. I find solutions based on my experience, research skills, strong knowledge and foundations in the subjects like Artificial Intelligence, Machine Learning, Data Mining, Optimization Techniques, Linear Algebra to mention a few. This is augmented by my high standard of coding skills which vary from C++, Java, Perl to Data Science languages such as Python, R and MATLAB. To further establish, it many of the my works have already been published online as research papers in well reputed journals. I have intense experience in Natural Language Processing applications such as summarization, search, retrieval, sentiment analysis, wordnet, deep learning. Having worked on real time implementations of various applications of Computer Science. The domains that I have worked on are Health Care System, Electronic Document Management Systems, Natural Text Mining, EDA, Web Development etc. Apart from profession, I have inherent interest in writing especially poems, stories, doing painting, cooking, photography, music to mention a few!

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s

%d bloggers like this: