Skip to main content

Posts

Showing posts from February, 2017

Helping the Blind See

The Sense of Vision is taken for granted by us in our day to day life, but only a visually impaired person can understand the true value and necessity of Vision. But soon AI based computer vision systems can help the blind and visually impaired to navigate.
Tech giants like Google, Baidu, Facebook, Microsoft are working on a range of products that apply Deep Learning for the Visually Impaired. One of them being Image Captioning technology wherein the system describes the content of an image.  To accelerate further research and to boost the possible applications of this technology, Google made the latest version of their Image Captioning System available as an open source model in Tensorflow. It’s called “Show And Tell: A Neural Image Caption Generator”. The project can be found at https://github.com/tensorflow/models/tree/master/im2txt and the full paper can be found at https://arxiv.org/abs/1609.06647
The Show and Tell model is an example of an encoder-decoder neural network. It works …

The Importance of Intents and Context in Chatbots

Humans are good in conversations, because they can understand the intent of any statement, also the context in which the statement is placed.
Today’s chatbots are equipped with intent recognition engine. Using machine learning, statements are mapped to intents, and the chabot can handle infinite variations of the same statement. Why is this technique useful? The following example cites this:
Consider you want to ask the contact details of a company. Now every person will ask it in a different way. Following are few of the variations that are possible:
Please share your contact details Where do you reside Where are you located Can you share your location Please provide your address Now the intent of the above questions is “asking address”. So a answer can be mapped to the intent, rather than all the questions. This helps in managing the chatbot easy.
Before intent recognition came into existence, most popular being Wit.ai, recently acquired by Facebook, earlier chatbots were purely based on A…

In the World of Document Similarity

How does a human infer whether two documents are similar? This question has dazzled cognitive scientists, and is one area under which a lot of research is taking place. As of  now there is no product that is able to match or surpass human capability in finding the similarity in documents. But things are improving in this domain, and companies such as IBM and Microsoft are investing a lot in this area.
We at Cere Labs, an Artificial Intelligence startup based in Mumbai, also are working in this area, and have applied LDA and Word2Vec techniques, both giving us promising results:
Latent Dirichlet Allocation (LDA): LDA is a technique used mainly for topic modeling. You can leverage on this topic modeling to find the similarity between documents. It is assumed that more the topics two documents overlap, more are the chances that those documents carry semantic similarity.
You can study LDA in the following paper: https://www.cs.princeton.edu/~blei/papers/BleiNgJordan2003.pdf
You can implement …