We are a chatbot startup (https://talkbot.io), on BETA right now. We want to train our own AI algorithms for NLP. We've got data but we are lost in what's the best way to use it for training an NLP algorithm.<p>I did the Andrew Ng Machine Learning course last year and have worked with ML and NN before, but never done something complex with words, semantics and syntax.<p>Are there any good online resources for learning how to train algorithms for NLP? Where should we start?<p>P.S. We are also looking for talented people to join the team.
Which one are you trying to accomplish?<p>-Sentiment analysis<p>-Syntactic analysis<p>-Entity analysis<p>Google Cloud Natural Language API Documentation
Natural Language API Basics<p>Contents
Natural Language features
Basic Natural Language requests
Specifying text content
Sentiment analysis<p>This document provides a guide to the basics of using the Google Cloud Natural Language API. This conceptual guide covers the types of requests you can make to the Natural Language API, how to construct those requests, and how to handle their responses. We recommend that all users of the Natural Language API read this guide and one of the associated tutorials before diving into the API itself.<p>Natural Language features<p>The Natural Language API has several methods for performing analysis and annotation on your text. Each level of analysis provides valuable information for language understanding. These methods are listed below:<p>Sentiment analysis inspects the given text and identifies the prevailing emotional opinion within the text, especially to determine a writer's attitude as positive, negative, or neutral. Sentiment analysis is performed through the analyzeSentiment method. Currently, only English is supported for sentiment analysis.<p>Entity analysis inspects the given text for known entities (proper nouns such as public figures, landmarks, etc.) and returns information about those entities. Entity analysis is performed with the analyzeEntities method.
Syntactic analysis extracts linguistic information, breaking up the given text into a series of sentences and tokens (generally, word boundaries), providing further analysis on those tokens. Syntactic Analysis is performed with the analyzeSyntax method.