Chatbot - Possible to call Watson API to respond user queries? - nlp

Chatbot has been developed using IBM bulemix to respond the user queries of grade one students.
Suppose a question raised "What is the life cycle of the leaf?" As of now, Chatbot has no entities related to leaf, life cycle etc..
Chatbot identifies the above query as an irrelevant entity. For the above case is it possible call any Watson knowledge API to answer the above queries?
Or
Can we make any third party searches (google/bing).
Or
the only option we need teach more relevant entities to the chatbot

You can use Watson-Discovery Tool
https://www.ibm.com/watson/services/discovery/

As #Rabindra said, you can use Discovery. IBM Developers built one example using Conversation and Discovery service using Java. And I built one example using Node.js based on the Conversation simple example. You can read the README and will understand how it works.
Basically, you need to know: this example has one action variable to call for Discovery when don't have the "relevant information" for an answer to the user and the Discovery service is called for get relevant answers.
You can see more about in this video from Official IBM Watson channel.
See more about Discovery Service.
See the API Reference for using Discovery Service.

You can also check entity linking service from Bing: https://azure.microsoft.com/en-us/services/cognitive-services/entity-linking-intelligence-service/. It is in preview for now, so you will get limited queries per second but it is free for use.

Related

Dialogflow Integrations (Using the fulfillment webhook model versus API interactions model)

I am trying to understand the different model in building a bot using dialogflow and came across this 2 methods.
Fulfillment model (with webhook enabled) documentation here
API Interactions documentation here
I understand that both of this models have their own pros and cons, and I understand how they both work. Most online examples are showing the fulfillment method (I guess that's more common?)
However, I would still like to ask what reason will it be to choose one or the other? If anyone had used either model before, what limitations are there?
p/s: I've look through quite a number of tutorials, and read through the dialogflow documentation.
the integration by fulfillment is indeed the default approach because you use DialogFlow to design your conversation flow and (big bonus) manage the integration with the various channels (ie Telegram, Facebook).
It is the easiest way to design a fully fledge conversation, you only need to worry about the post hooks that are sent to your backend to either save the data or alter the conversation (add contexts or trigger events).
Important remark: all user traffic (who says what) goes via Dialogflow cloud
The API interaction becomes a good option when you have already an existing frontend (say an existing application or web sites) and you want to plug in DialogFlow NLP capabilities.
I have done something like that to create a FAQ chatbot that called DialogFlow to identify which intent would match a certain phrase while the BOT was deployed in MS Teams.
The architecture would indeed look like the one in the documentation: MS Team ecosystem is the "End-User" part, then my Java app ("Your System") would use the API to call DialogFlow.
Important remark: only given statements (the ones you send) go to Dialogflow cloud

Setting Dialogflow Context using Actions Sdk

I'm currently experiencing issues with Google's user storage object. This used to work fine, but lately different actions and environments have stopped working due to the user storage not persisting past the first intent. When investigating the issue I ran into the a stackoverflow post. It recommends to change from the Dialogflow SDK to the actionsOnGoogle SDK when you are having problems like this.
I've tried doing this, but when I change to the actions SDK I can no longer interact with the dialogflow context code.
Does changing to the actionSDK change anything about how the user storage works and if so, is it possible to migrate to the actionsSDK and keep using the dialogflow contexts?
Yes, of course you can manage the "context" of the conversation in an SDK Action but no, it is not "just like" DialogFlow. Take a look at the "data" and "userStorage" members of the conversation object. The former is used to store data across turns of a single conversation. The latter is used to persist data across conversations with your Action.

Microsoft Bot Framework - very high response times

I have 10 seconds response times through any channel. (WebChat and Facebook)
My endpoint is a PAAS instance located in the western United States.
The WebApp has an S3 size and the response times are constant (even if there is only one conversation).
I have the following questions:
Is there any way to optimize this?
What are the Azure Bot Framework SLAs?
As bot framework is a preview product, there is no current SLAs.
Are you using the default state storage? If so, part of the slow down you mentioned is probably related. We highly recommend implementing your own state service. There is a blog article here discussing the implementations there is also a repository here with samples. This is probably not 100% of your issue but it is probably at least part of it.
Another thing to keep in mind is where your bot is located in relationship to your WebChat client and what instance of the Bot Connector you are using this blog may provide more info. Please see the "Geographic Direct Line endpoints" section.

How to implement BOT engine like WIT.AI for on an on-premise solution?

I want to build a chatbot for a customer service application. I tried SaaS services like Wit.Ai, Motion.Ai, Api.Ai, LUIS.ai etc. These cognitive services find the "intent" and "entities" when trained with the typical interactions model.
I need to build chatbot for on-premise solution, without using any of these SaaS services.
e.g Typical conversation would be as following -
Can you book me a ticket?
Is my ticket booked?
What is the status of my booking BK02?
I want to cancel the booking BK02.
Book the tickets
StandFord NLP toolkit looks promising but there are licensing constraints. Hence I started experimenting with the OpenNLP. I assume, there are two OpenNLP tasks involved -
Use 'Document Categorizer' to find out the intent
Use 'Named Entity Recognition' to find out entities
Once the context is identified, I will call my application APIS to build the response.
Is it a right approach?
How good OpenNLP is in parsing the text?
Can I use Facebook FASTTEXT library for Intent identification?
Is there any other open source library which can be helpful in building the BOT?
Will "SyntaxNet" be useful for my adventure?
I prefer to do this in Java. BUT open to node or python solution too.
PS - I am new to NLP.
Have a look at this. It says it is an Open-source language understanding for bots and a drop-in replacement for popular NLP tools like wit.ai, api.ai or LUIS
https://rasa.ai/
Have a look at my other answer for a plan of attack when using Luis.ai:
Creating an API for LUIS.AI or using .JSON files in order to train the bot for non-technical users
In short use Luis.ai and setup some intents, start with one or two and train it based on your domain. I am using asp.net to call the Cognitive Service API as outlined above. Then customize the response via some JQuery...you could search a list of your rules in a javascript array when each intent or action is raised by the response from Luis.
If your Bot is english based, then I would use OpenNLP's sentence parser to dump the customer input into a database (I do this today). I then use the OpenNLP tokenizer and push the keywords (less the stop words) and Parts of Speech into a database table for keyword analysis. I have a custom Sentiment model built for OpenNLP that will tag each sentence with a Pos, Neg, Neutral sentiment...You can then use this to identify negative customer service feedback. To build your own Sentiment model have a look at SentiWord.net and download their domain agnostic data file to build and train an OpenNLP model or have a look at this Node version...
https://www.npmjs.com/package/sentiword
Hope that helps.
I'd definitely recommend Rasa, it's great for your use case, working on-premise easily, handling intents and entities for you and on top of that it has a friendly community too.
Check out my repo for an example of how to build a chatbot with Rasa that interacts with a simple database: https://github.com/nmstoker/lockebot
I tried RASA, But one glitch I found there was the inability of Rasa to answer unmatched/untrained user texts.
Now, I'm using ChatterBot and I'm totally in love with it.
Use "ChatterBot", and host it locally using - 'flask-chatterbot-master"
Links:
ChatterBot Installation: https://chatterbot.readthedocs.io/en/stable/setup.html
Host Locally using - flask-chatterbot-master: https://github.com/chamkank/flask-chatterbot
Cheers,
Ratnakar
With the help of the RASA and Botkit framework we can build the onpremise chatbot and the NLP engine for any channel. Please follow this link for End to End steps on building the same. An awsome blog that helped me to create a one for my office
https://creospiders.blogspot.com/2018/03/complete-on-premise-and-fully.html
First of all any chatbot is going to be the program that runs along with the NLP, Its the NLP that brings the knowledge to the chatbot. NLP lies on the hands of the Machine learning techniques.
There are few reasons why the on premise chatbots are less.
We need to build the infrastructure
We need to train the model often
But using the cloud based NLP may not provide the data privacy and security and also the flexibility of including my business logic is very less.
All together going to the on premise or on cloud is based on the needs and the use case of the requirements.
How ever please refer this link for end to end knowledge on building the chatbot on premise with very few steps and easily and fully customisable.
Complete On-Premise and Fully Customisable Chat Bot - Part 1 - Overview
Complete On-Premise and Fully Customisable Chat Bot - Part 2 - Agent Building Using Botkit
Complete On-Premise and Fully Customisable Chat Bot - Part 3 - Communicating to the Agent that has been built
Complete On-Premise and Fully Customisable Chat Bot - Part 4 - Integrating the Natural Language Processor NLP
Disclaimer: I am the author of this package.
Abodit NLP (https://nlp.abodit.com) can do what you want but it's .NET only at present.
In particular you can easily connect it to databases and can provide custom Tokens that are queries against a database. It's all strongly-typed and adding new rules is as easy as adding a method in C#.
It's also particularly adept at turning date time expressions into queries. For example "next month on a Thursday after 4pm" becomes ((((DatePart(year,[DATEFIELD])=2019) AND (DatePart(month,[DATEFIELD])=7)) AND (DatePart(dw,[DATEFIELD])=4)) AND DatePart(hour,[DATEFIELD])>=16)

AFIncrementalStore with Parse

I am developing an social app on iOS that have many-to-many relation, local persistency, and user interaction. I have tried using native Parse API in iOS and find it too cumbersome to do all the client-server logic. So my focus shifted to finding a syncing solution.
After some research I found AFIncrementalStore quite easy to use and it's highly integrated in CoreData. I just started to work on this and I have two questions to ask:
1) How to do the authentication process? Is it in AFRESTClient?
2) How to set up AFRESTClient to match Parse's REST API? (an example would be great!)
P.S. I also found FTASync, which seems to be another solution. Any thought on this framework?
Any general suggestion on client-server syncing solutions will be highly appreciated!
Thanks,
Lei Zhang
Back with iOS 5 Apple silently rolled out NSIncrementalStore to manage connection between APIs and persistent stores. Because I couldn't word it better myself:
NSIncrementalStore is an abstract subclass of NSPersistentStore designed to "create persistent stores which load and save data incrementally, allowing for the management of large and/or shared datasets". And while that may not sound like much, consider that nearly all of the database adapters we rely on load incrementally from large, shared data stores. What we have here is a goddamned miracle.
Source: http://nshipster.com/nsincrementalstore/
That being said, I've been working on my own NSIncrementalStore (built specifically for Parse and utilizing the Parse iOS/OS X SDK) and you're welcome to check out/use/contribute to the project at https://github.com/sbonami/PFIncrementalStore.
Take a look at this StackOverflow question and at Chris Wagner's article on raywenderlich.com.
The linked SO question has examples for how to include the authentication token with each request to Parse. So you'll just need to have the user log in first, and store their token to include it with each subsequent request.
Chris Wagner's tutorial has a sample AFHTTPClient named SDAFParseApiClient to communicate with the Parse REST API. You'd have to adapt it to be an AFRESTClient subclass, but it should give you a start.
Some other thoughts between the two solutions you're considering:
AFIncrementalStore does not allow the user to make any changes without a network connection, while FTASync keeps a full Core Data SQLite store locally and syncs changes to the server when you tell it to.
FTASync requires you to make all your synched managed objects subclasses of FTASyncParent, with extra properties for sync metadata. AFIncrementalStore keeps its metadata behind the scenes, not in your model.
FTASync appears not to be widely used and hasn't been updated in over a year; if you use it you will likely be maintaining it.

Resources