This is an automated email from the ASF dual-hosted git repository.
aradzinski pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/incubator-nlpcraft-website.git
The following commit(s) were added to refs/heads/master by this push:
new 8bee157 Update quick_intro_apache_nlpcraft.html
8bee157 is described below
commit 8bee157229df600f699223d7bd3fda8292d81a40
Author: Aaron Radzinski <[email protected]>
AuthorDate: Sun Mar 28 09:48:08 2021 -0700
Update quick_intro_apache_nlpcraft.html
---
blogs/quick_intro_apache_nlpcraft.html | 51 ++++++++++++++++++++--------------
1 file changed, 30 insertions(+), 21 deletions(-)
diff --git a/blogs/quick_intro_apache_nlpcraft.html
b/blogs/quick_intro_apache_nlpcraft.html
index 6071a48..c615044 100644
--- a/blogs/quick_intro_apache_nlpcraft.html
+++ b/blogs/quick_intro_apache_nlpcraft.html
@@ -31,7 +31,8 @@ publish_date: November 16, 2020
</div>
<p>
In this short article I would like to introduce Apache NLPCraft - an
open source library for adding Natural
- Language Interface to any application. The goal of this project from
its inception in 2017 was and still is
+ Language Interface to any application. It enables people to interact
with your products using voice
+ or text. The goal of this project from its inception in 2017 was and
still is
unambiguously straightforward - provide an efficient & highly
productive API to develop advanced NLP-based
interfaces for modern applications.
</p>
@@ -48,15 +49,17 @@ publish_date: November 16, 2020
<div class="container-fluid" style="padding: 0">
<div class="row">
<div class="col-6">
- <b>Programmable Intents</b><br/>
+ <b>Intent Definition Language</b><br/>
<p>
- Fully programmable, advanced intent DSL with deterministic
matching provides easy to use and expressive mechanism for a complex intent
logic.
+ Advanced <a href="/intent-matching.html">Intent Definition
Language</a> (IDL) coupled with deterministic intent matching
+ provide ease of use and unprecedented expressiveness for
designing real-life, non-trivial intents.
</p>
</div>
<div class="col-6">
- <b>Java First</b><br/>
+ <b>Composable Named Entities</b><br/>
<p>
- REST API and Java-based implementation natively supports
the world's largest ecosystem of development tools, multiple programming
languages, frameworks and services.
+ Easily compose, mix and match new named entities out of
built-in or external ones, creating new
+ reusable named entity recognizers on the fly.
</p>
</div>
</div>
@@ -64,27 +67,30 @@ publish_date: November 16, 2020
<div class="col-6">
<b>Model-As-A-Code</b><br/>
<p>
- Model-as-a-code convention natively supports any
development life cycle tools and frameworks in the Java ecosystem.
+ Everything you do with NLPCraft is part of your source
code. No more awkward web UIs
+ splitting your logic across different incompatible places.
Model-as-a-code is built by
+ engineers, and it reflects how engineers work.
</p>
</div>
<div class="col-6">
- <b>Any Data Source</b><br/>
+ <b>Java First</b><br/>
<p>
- NLPCraft can work with any data source, device, or service
- public or private. From databases and SaaS systems, to smart home devices,
voice assistants and chatbots.
+ REST API and Java-based implementation natively supports
the world's largest ecosystem of development tools,
+ multiple programming languages, frameworks and services.
</p>
</div>
</div>
<div class="row">
<div class="col-6">
- <b>Short-Term-Memory</b><br/>
+ <b>Any Data Source</b><br/>
<p>
- Advanced out-of-the-box support for maintaining and
managing conversational context that is fully integrated with intent matching.
+ NLPCraft can work with any data source, device, or service
- public or private. From databases and SaaS systems, to smart home devices,
voice assistants and chatbots.
</p>
</div>
<div class="col-6">
- <b>Composable Named Entities</b><br/>
+ <b>Short-Term-Memory</b><br/>
<p>
- Compose new reusable Named Entities out of existing
internal or external ones, build new ones and mix and match using comprehensive
DSL.
+ Advanced out-of-the-box support for maintaining and
managing conversational context that is fully integrated with intent matching.
</p>
</div>
</div>
@@ -188,7 +194,8 @@ publish_date: November 16, 2020
<p>
In NLPCraft the default built-in approach for detecting NEs is a
synonym matching. For each NE you provide
a list of synonyms by which it will be found in the input text. To
make this task really simple NLPCraft
- comes with a set of tools including macros and Synonym DSL. Here’s the
static model configuration for our
+ comes with a set of tools including <a
href="/data-model.html#macros">Macro DSL</a> and <a
href="/intent-matching.html">Intent Definition Language</a> (IDL).
+ Here’s the static model configuration for our
example as <code>lightswitch_model.yaml</code> file that includes NE
definitions and one intent:
</p>
<pre class="brush: js, highlight: [14, 21, 29, 38]">
@@ -242,20 +249,21 @@ publish_date: November 16, 2020
</ul>
</li>
<li>
- We grouped <code>"ls:on"</code> and <code>"ls:off"</code> into
group <code>"act"</code> for easier use in intent.
+ We grouped <code>"ls:on"</code> and <code>"ls:off"</code> into
group <code>"act"</code> for easier use in the intent.
</li>
<li>
- Each model element is defined through synonyms using macros and
Synonym DSL which is similar to Regular Expressions.
+ Each model element is defined through synonyms using <a
href="/data-model.html#macros">Macro DSL</a>.
</li>
<li>
- Intent <code>"ls"</code> uses Intent DSL. In short - this intent
will match if we can detect one element
+ Intent <code>"ls"</code> uses <a
href="/intent-matching.html">Intent Definition Language</a>. In short - this
intent
+ will match if we can detect one element
from the group <code>"act"</code> and zero or more
<code>"ls:loc"</code> elements in any order.
</li>
</ul>
<p>
- Notice that macros and Synonym DSL allow you to define hundreds and
often thousands of synonyms for each model
+ Notice that <a href="/data-model.html#macros">Macro DSL</a> allow you
to define hundreds and often thousands of synonyms for each model
element with only a few lines of YAML (or JSON). In the above model,
for example, the three elements have <b>over
- 7,700 unique synonyms</b> after all macros and Synonym DSL expansions.
+ 7,700 unique synonyms</b> after all <a
href="/data-model.html#macros">Macro DSL</a> processing.
</p>
<p>
Now, dealing with synonyms may sound limiting at first. It is,
however, a surprisingly powerful and flexible mechanism
@@ -264,7 +272,8 @@ publish_date: November 16, 2020
<ul>
<li>
Synonyms can be developed, extended and tested using many tools
that NLPCraft provides like
- macros, Synonym DSL and synonym suggester (that uses Google’ BERT
and Facebook fastText models).
+ <a href="/data-model.html#macros">Macro DSL</a>, <a
href="/intent-matching.html">Intent Definition Language</a> and
+ <a href="/tools/syn_tool.html">Synonym Suggester</a> (that uses
Google’ BERT and Facebook fastText models).
</li>
<li>
Classic NLP problems like word-sense disambiguation (“bass” the
fish, and “bass” the sound) are
@@ -285,7 +294,7 @@ publish_date: November 16, 2020
</p>
</section>
<section>
- <h2 clas="section-title">Intent Matching</h2>
+ <h2 class="section-title">Intent Matching</h2>
<p>
Although full explanation of the <a
href="/intent-matching.html">intent matching</a> algorithm is outside the scope
of this article, the basic workflow looks like this:
</p>
@@ -361,7 +370,7 @@ publish_date: November 16, 2020
We’ll leave outside of this article the details of the particular
integration with HomeKit or Arduino devices. We’ll also defer
to the NLPCraft <a href="/docs.html">documentation</a> to learn about
other topics such as
<a href="/basic-concepts.html#stm">conversation management</a>,
- details of <a href="/intent-matching.html">Intent and Synonym DSLs</a>,
+ details of <a href="/data-model.html#macros">Macro DSL</a> and <a
href="/intent-matching.html">Intent Definition Language</a>,
built-in <a href="/tools/test_framework.html">testing tools</a>,
3rd party NER <a href="/integrations.html">integrations</a>, etc.
</p>
