There was something wrong with fetching your inbox. Please contact support here.
Sophisticated pattern recognition of unstructured data for Natural Language Processing
Analyze, classify, and categorize content using Machine Learning APIs
The Text Analysis APIs from HPE Haven OnDemand provide functions that allow you to process websites, text and hundreds of data file formats. The Text Analysis APIs include APIs for Sentiment Analysis, Named Entity Extraction, Document Classification, Document Categorization, and more. While these APIs are traditionally used standalone, they can also be orchestrated and called together using HPE Haven OnDemand Combinations e.g. to analyze a document file with Sentiment Analysis, Entity Extraction, and Concept Extraction, then index the extracted data using a single Combination API call. Extracting meaningful insights from unstructured data has never been so simple.
The Auto Complete API allows you to expand a prefix into a list of possible words that the prefix matches. You can use this API to provide search suggestions.
The Concept Extraction API allows you to provide some input text or a document, and the API returns the best terms and phrases. You can use the results as a quick summary of the contents of a document, to highlight key phrases, or to generate links between unstructured information.
The Entity Extraction API allows you to find useful snippets of information from a larger body of text that match more than 70 entity types. The snippets of information (known as entities) can be words, phrases, or other blocks of information, such as a phone number. You provide the text to analyze and choose the kind of information that you want to find. The API provides a set of entity types, which includes people names, place names, company names, phone numbers, dates, Web addresses, and credit card numbers.
The Highlight Text API finds specified terms in your input text and adds HTML tag around them. It returns your input text, with the added HTML tags. Haven OnDemand highlighting applies language stemming rules to highlight words with the same root, which means that it can highlight all the information in the text that is relevant to the search term or the highlight expression of your choice.
The Sentiment Analysis API analyzes text to return the sentiment as positive, negative, neutral, or mixed for each topic found. Additionally it provides an overall score of the aggregate sentiment for the entire text. It contains a dictionary of positive and negative words of different types, and defines patterns that describe how to combine these words to form positive and negative phrases.
The Text Tokenization API helps you find more information about the terms that you might want to use in the Query Text Index API or other APIs. You provide a list of terms, or some text, and the API returns information about the terms in the text, including:
the weight that the term holds in the specified text indexes, based on Advanced Probabilistic Concept Modelling (APCM).
the number of documents that the term occurs in, in the specified text indexes.
the total number of times that the term occurs, in the specified text indexes.
The Classify Document API allows you to classify documents into different collections and understand which conditions caused the classification.
The Document Categorization API allows you to find the categories that a document matches. You can think of this process as the inverse of a normal query. You provide a document to the API, and it returns a list of the categories in your custom values category text index that match it.
The Expand Terms API returns a list of terms that match a term that you provide, according to a specified expansion. There are three different expansions available: Fuzzy, returns a list of words with a similar spelling to the word you provide. Stem, returns a list of terms that have the same stem as the word you provide. Wild, returns a list of the terms that match a wildcard term that you provide.
The Language Identification API analyzes a piece of text that you provide and returns the language of the text. The API returns the language and the encoding, and details of the UTF-8 character ranges that the input text includes. You can use Language Identification to determine the correct language settings to use for other Haven OnDemand APIs, such as Sentiment Analysis or Entity Extraction.
For any input format, the Text Statistics API extracts the text and returns statistical information about the contents, such as the number of terms, and the percentage of different types of character (alphabetic, numeric, punctuation, and so on).
HPE Haven OnDemand provides more than 70 REST APIs for rapid integration in enterprise, mobile, desktop, IoT, augmented reality, virtual reality, and web apps. Reimagine your world and accelerate development with Applied Machine Learning from Haven OnDemand.