Instantly add voice to your business.
Add voice and text (everyday English) to your current web-based, mobile or embedded applications. Let us call your API's from our Conversation Server.
Online applications interface through
a GUI in a browser or mobile app.
Here's how our pipeline can voice-enable and
text-enable your current applications.
Conversations server (NLU Pipeline, below) converses with the user, gathers and clarifies information, calls the same API’s as your mobile app, browser or embedded interface. Integration typically takes a couple of days—we'll help you do it.
Really understand your customers.
Get control over Machine Learning (ML) generated answers. How? By complementing your ML software (Virtual Agent, chatbot, IA) with our massively rule-based NLU pipeline.
Our rule-based pipeline working side-by-side with your ML software will enable your chatbot to answer more precisely.
Get the best of both worlds:
Coverage and Precision!
Machine Learning (your code) provides coverage. Rule-based (our pipeline, below) provides precision and control over answers.
Our massively rule-based approach helps your ML-based NLU software:
- Make sense of more user utterances. Better deal with UMM (unsupported, misunderstood, mismatched utterances).
- Extract ALL the entities and relations, modality and negation from utterances.
- Handle out-of- turn utterances.
- Handling more dialogue acts, including user clarification requests. Use reinforcement learning to take the user's sentiment into account when answering.
- Co-reference resolve pronouns, nouns, adverbials.
- Use context to resolve ellipsis (missing verbs, nouns, etc) and do co-reference resolution.
- Handle complex dialogue graphs, where the next prompt depends on the user's answer to a previous question.
- Instantly add voice and text to your existing GUI based interfaces
North Side Natural Language Understanding (NLU) pipeline
North Side presentation Feb 6, 2018
Come back here to download the whitepaper after the conference