Imagine if the things around your house could respond to your voice even when you were shouting over a smoke alarm, keep track of each individual wandering through the house, unlock your front door just by identifying your voice, and even identify your emotions. Those are all capabilities that Microsoft is preparing to add to its Project Oxford, a set of cloud-based machine learning services introduced last May at Microsoft's Build conference. Ars took a deep dive on Project Oxford's first wave of machine learning-based services last year. Those services performed a number of image processing and recognition tasks, offered text-to-speech and speech recognition services, and even converted natural language into intent-based commands for applications. The services are the same technology used in Microsoft's Cortana personal assistant and the Skype Translator service, which translates voice calls in six languages (and text messages in 50 languages) in real-time.
We have been profiling a number of machine learning APIs lately, not because there is an opportunity to proxy and stream the APIs, but because of the possibilities around applying common machine learning models to the data and content streams our customers are producing. One of the interesting machine learning APIs we are profiling currently is called ParallelDots, which provide a suite of common, yet powerful machine learning models that anyone can integrate into their applications. As we profile the ParallelDots API, we are considering the possibilities for trickling, or streaming updates via the APIs our customer's are proxying using our service. Consider some of the opportunities for posting stream updates to any of the following APIs: - Sentiment - Sentiment API accepts input text, language code and API key to return a JSON response classifying the input text into a sentiment. API can extract this information from any type of text, web page or social media network.
Historically, building a system that can answer natural language questions about any image has been considered a very ambitious goal. So, how many players are in the image? Well, we can count them and see that there are eleven players, since we are smart enough not to count the referee, right? Although as humans we can normally perform this task without major inconveniences, the development of a system with these capabilities has always seemed closer to science fiction than to the current possibilities of Artificial Intelligence (AI). However, with the advent of Deep Learning (DL), we have witnessed enormous research progress in Visual Question Answering (VQA), in such a way that systems capable of answering these questions are emerging with promising results. In this article I will briefly go through some of the current datasets, approaches and evaluation metrics in VQA, and on how this challenging task can be applied to real life use cases.
Humans have the unique capacity to translate thoughts into words, and to infer others' thoughts from their utterances. This ability is based on mental representations of meaning that can be mapped to language, but to which we have no direct access. The approach to meaning representation that currently dominates the field of natural language processing relies on distributional semantic models, which rest on the simple yet powerful idea that words similar in meaning occur in similar linguistic contexts1. A word is represented as a semantic vector in a high-dimensional space, where similarity between two word vectors reflects similarity of the contexts in which those words appear in the language2. More recently, these models have been extended beyond single words to express meanings of phrases and sentences5,6,7, and the resulting representations predict human similarity judgments for phrase- and sentence-level paraphrases8,9.
There's an awful lot of text data available today, and enormous amounts of it are being created on a daily basis, ranging from structured to semi-structured to fully unstructured. What can we do with it? Well, quite a bit, actually; it depends on what your objectives are, but there are 2 intricately related yet differentiated umbrellas of tasks which can be exploited in order to leverage the availability of all of this data.
Text analysis, as a whole, is an emerging field of study. Fields such as Marketing, Product Management, Academia, and Governance are already leveraging the process of analyzing and extracting information from textual data. We discussed the technology behind Text Classification, one of the essential parts of Text Analysis. Text classification or Text Categorization is the activity of labeling natural language texts with relevant categories from a predefined set. In laymen terms, text classification is a process of extracting generic tags from unstructured text. These generic tags come from a set of pre-defined categories. Classifying your content and products into categories help users to easily search and navigate within website or application.
This tutorial goes over some basic concepts and commands for text processing in R. R is not the only way to process text, nor is it really the best way. Python is the de-facto programming language for processing text, with a lot of builtin functionality that makes it easy to use, and pretty fast, as well as a number of very mature and full featured packages such as NLTK and textblob. Basic shell scripting can also be many orders of magnitude faster for processing extremely large text corpora -- for a classic reference see Unix for Poets. Yet there are good reasons to want to use R for text processing, namely that we can do it, and that we can fit it in with the rest of our analyses.
The Semantic Web Company (SWC) is a leading provider of software and services in the areas of Semantic Information Management, Machine Learning, Natural Language Processing, and Linked Data technologies. SWC's renowned PoolParty Semantic Suite software platform is used in large enterprises, Government Organizations, NPOs and NGOs around the globe to extract meaning from big data.