Natural Language Processing Engine
AI as a service
APIs exposing the Alterra Deep Learning AI algorithms
-
01
A semantic classifier for questions and commands. AI to power intelligent agents, Alexa skills and IoT devices.
Learn more
API documentation -
02
Semantic question answering. AI to drive customer service chatbots, customer support automation and natural language search on your website and in apps.
Learn more
API documentation -
03
Extract entities from phrases. Convert free-text user queries to SQL-like structured queries that can be submitted to databases. Fill out forms via chat, with infinite context, random access navigation, etc.
Learn more -
04
Time and Date API
This API extracts time and dates from free text and returns them in a structured form, e.g., "what if we go next Sunday morning and return between Nov 11 and 13?". It's more comprehensive and accurate than most other solutions and pre-trained so no further training is required.
API documentation
Call us -
05
Alterra Travel API
Sell flights and hotels via chat. The API takes a free-form user query and extracts all of the parameters such as locations, dates, target prices, class of service, amenities, etc. and returns them in a structured form. Pass these structured queries to a GDS or your booking engine. With a pre-trained RNN inside, no further training is required.
API documentation -
06
Destination Recommendation Engine
Recommend leisure travel destinations by activities or themes, e.g., "find me a 7-day vacation for two in unspoiled nature, with good biking."
Call us
Alterra Phraser API
A semantic classifier for questions and commands
AI to power intelligent agents, chatbots, Alexa skills and IoT devices
Converts
natural language questions and commands into a canonical form that computers can understand.
Deep Learning
eliminates the need for rules-based coding.
The Alterra NLP engine is 1,000x faster than RNN and more accurate.
Features
- The Intent classifier (paraphrase detector) for natural language questions and commands
- Phraser takes questions in a multitude of semantically equivalent ways and reduces these paraphrases to one canonical form
- Your program can reply with a text or call any other function
- Powered by Alterra's phrase2vec sequence embedding algorithm - it's like word2vec, but for multiple-word questions and commands
- More accurate than competing intent classifiers and chatbot frameworks: P@1=90%
- 1,000x faster than a typical RNN
- Runs on plain vanilla CPU – no GPU/TPU is required
- Humans can train the neural network to make it even more accurate
02 Question answering
Convert your static FAQ to a question-answering system
AI to power conversational virtual agents, knowledge base search or call center automation
Alterra FAQ API
Semantic question answering
API access to Alterra Answers
Automate
sales, support, internal IT, onboarding
Deep Learning
no rules-based coding required
Features
- Natural-language search for FAQs, help centers, knowledge bases, user guides, canned responses
- Use fully autonomously or pair up with live agents
- Users may ask questions in their own words
- Search by meaning, not keywords
- Powered by Alterra's phrase2vec sequence embedding algorithm
- More accurate than the Google custom search engine and other FAQ search solutions
- Humans can train the neural network to make it even more accurate
Alterra FAQ API
AI to power customer service chatbots, customer support automation and natural language search on your website.
Alterra FAQ Editor
Create or import your FAQ file; edit it online
Label the training set to improve ML quality
Optional – you can also do everything via the API
Convert free-text user queries to SQL-like structured queries that can be submitted to databases.
Deep Learning (LSTM) inside – no keywords, no regexs – just feed your training corpus into the neural network.
98% per-label precision
Features
- Slot filler for natural language queries
- The API takes free-form user query, extracts all parameters and returns them in a structured form that can be submitted to databases
- Powered by Alterra's recurrent neural network (two bi-directional residual LSTMs)
- Supervised learning: a labeled training set is required (e.g., a chat or call log)
- More accurate than most competing slot fillers: ~98% per-slot precision
- Example: Alterra travel API – parses flight and hotel reservation requests
- Upload your training set here or contact us