Got questions? We got Answers™

Introducing Avaamo Answers™

An AI-powered knowledge base that gives you the Answers™

Combining artificial intelligence, automation, and virtual assistants, Avaamo Answers™ generates an intelligent, conversational knowledge base from all your company’s documents, providing relevant and accurate information to your customers or employees.

Can’t find what your looking for?

Enterprises have a wealth of information buried in documents. Whether that data is on the company website or intranet, file storage app, or content management system, it takes a lot of work to find the right file, let alone locate specific information embedded in a document. More often than not, it’s easier and more effective to ask a seasoned colleague for the answer.

 

But what if you have a seasoned “virtual” colleague who’s already read and memorized information from your company’s documents — everything from the employee handbook to product manuals — and can answer your question with an exact answer?

Here’s the Answer™

Avaamo Answers uses cutting-edge AI and deep learning technology to unlock your content and make information from vast amounts of enterprise documents useful again. By automatically classifying, extracting and enriching unstructured data from ingested documents, Avaamo Answers learns what information is relevant to deliver contextual responses.

 

Our data understanding pipeline incorporates proprietary bidirectional language models as well as domain-specific models to do what others can’t — learn about your content, understand what users are asking, and deliver precise answers conversationally.

THIS ISN’T KEYWORD SEARCH…

A fundamentally different approach to the problem

Smart Document Processing

Deep Learning technology that unlocks your content by automatically classifying, extracting and enriching ingested docs by categorizing content for answering and identifying entity relationships.

Participation of Domain Experts

Tooling to enable domain experts to train and refine the models for better domain understanding and accuracy

Conversational Experience

Simple natural language enabled experience via text and voice including disambiguation, relevancy based follow on questions, and contextualized response

Keyword based search is inexact & error-ridden

Enterprise Search Engines are keyword-based and don’t understand user queries or the document semantically. Hence, ends up with 100’s of results.

Search lacks context & follow up questions

Enterprise Search Engines treat each user query as different. It neither stores the context nor asks a follow up question to find answer.

Search lacks continuous learning

Domain experts cannot incorporate their knowledge or improve answers based on user feedback.

Search provides links, not answers

Search engines don’t give an answer but redirect users to a page — a bad user experience.

Search has limited integrations

Search doesn’t integrate to customer experience applications like Live Chat, Lead Management, Surveys, Recommendations, etc.

Search is not voice compatible

Search doesn’t lend itself to a voice based conversational experience.

Avaamo Answers Capabilities

Smart Document Understanding

Quickly ingest 1000’s of documents (PDFs, TXT files or URLs). Avaamo’s Deep Learning technology that powers the data understanding pipeline using both Deep Bidirectional language models as well as domain specific models. Pinpoint accurate sections in the document and highlight them inline.

Deep Learning with Expert Participation

Models are updated in real-time based on user feedback as well as additional content and supervised learning. User-friendly tooling that enables domain experts to train the generated knowledge to provide the correct answer. Full end-to-end visibility of conversational history and training based on answers. Pre-trained domain models improve accuracy of answers.

Conversational & Enterprise Ready

Integrated with Avaamo Conversational AI platform for an end-to-end voice and text  experience. Dialog flows for follow-on actions based on specific topics. Bidirectional handoff with live agents. Contextualized results based on who the user is, their location, their preferences etc. and integration to other applications. Enable on secure channels and enforce authentication for access. Both in-depth of content as well as additional dialog and voice experiences .

How It Works

Natural Language Understanding

Avaamo Answers uses our proprietary NLU technology, which has been proven battle-tested and deployed at scale, with millions of users worldwide. Avaamo’s NLU engine provides a core infrastructure already known in the market for its scalability, reliability, and accuracy. In addition, it has the ability to handle many prioritized inference tasks (co-referencing, negations, time reasoning, etc.) on the incoming user query. Our NLU technology offers advanced techniques in intent matching and disambiguation. It has a superior language-understanding ability to handle wide variances in user language such as identifying “bag of words”, domain syntax, misspelled words, and short form phrases.

BERT Technology

In addition to our proprietary NLU, Avaamo Answers leverages BERT technology (Bidirectional Encoder Representations from Transformers) as the base model, which provides the most advanced machine interpretability of language semantically. By implementing the BERT framework, we are able to achieve an unprecedented level of language understanding without human training, to retrieve relevant answers from a large corpus of text.

Context Awareness

Context awareness ensures relevant and precise answers. This entails semantic understanding of the user’s question and the content in context to the user’s query. Answers™ personalizes responses based on user’s location, role, and access, giving a precise answer rather than serving up links to multiple documents that cite policies or guidelines.

Specificity: Our approach to performing QA from a large set of documents is to retrieve relevant context out of underlying documents that may contain the answer. This reduced context is input to the reading comprehension model to fetch the final answer for the user query. To retrieve context from a question, we parse the uploaded content semantically and use various models to ascertain specificity, coupled with independent n-gram scoring and fetch the answer in context, based on semantic relevance of the user query.

Improving Accuracy: Signals including identity, location, previous answers—all multiple modes of answering—are combined and ranked to provide unambiguous results. This includes boosting probabilities based on linguistic post-processing of previous response in relation to the question type. Scores at each level of all probable answer candidates are browsed to suggest likely answers based on various hard-lines and then returned with a normalized confidence score.

Multi-Step Reasoning

While the retrieve-read approach is quite powerful, addressing queries that involves multi-step reasoning requires better insight into the specificity of the question. Avaamo Answers queries the user in a human-like manner to get clarification and narrow down the specificity before a question is answered. To handle complex queries, Avaamo Answers dynamically builds a knowledge graph around documents, support questions, and tickets around “Office 365 documents” to facilitate multi-step reasoning. This knowledge graph is created based on pre-built classification models to identify implicit vs. explicit relationships. Avaamo Answers’ knowledge graph is built in real time based on the content that is available, in order to answer queries with a level of specificity that is not available elsewhere in the market.

Learn about Answers™

Learn the latest on our breakthrough software Avaamo Answers™.  Make your knowledge base conversational.

Datasheet: Avaamo Answers™

 

 

Answers™ initiates a dialog with millions of documents buried in multiple silos across the enterprise.

resource-arrow

Whitepaper: Avaamo Answers™

 

 

Avaamo Answers™ technology delivers unique value to developers building Question Answering (QA) systems.

resource-arrow

Newsletter: Sign up for a Conversational AI newsletter, curated by Avaamo

Get the latest news on Conversational AI delivered to your email inbox every two weeks.

resource-arrow