Monthly Archives: September 2016

Dealing with off topics.

When building a conversational system, how you handle off topics tends to swing one way or the other for people new to it.

They either totally forget about handling chit-chat/off topic. This leads to the system feeling stupid to the end user, even if it has a high accuracy. Or feeling like a search engine.

Or they go the other way and try to answer everything they can possibly think of, without realising the rabbit hole they are going down. Also they may only put in one response to the same type of question, making it feel like a computer program.

The correct way to handle off topics is: Answer the topic not the question, and drive the user back to the intended usage of the conversational system! 

To give an example:

User: Hey Watson, do you love Siri?
Watson: I have never really thought about other AI systems. I am too busy selling goods for pets.

User: Please tell me if you love Siri.
Watson: I would much prefer to help you in buying things for your pet, rather then talking about Artificial intelligences.

User: But do you love Siri?
Watson: Can we please get back to buying things for your pet.

The first response detects that the person is talking about an “AI” related item. But instead of trying to expend time on the nature of the question, you can deflect it with a broad response.

The second response is the same but a bit cooler, and pushing the user back to the topic.The last response stops playing with the user.

You can achieve this quite easily with the following advanced output.

{
  "output": {
    "text": {
      "values": [
       "I have never really thought about other AI systems. I am too busy selling goods for pets.",
       "I would much prefer to help you in buying things for your pet, rather then talking about Artificial intelligences.",
       "Can we please get back to buying things for your pet."
      ],
      "selection_policy": "sequential"
    }
  }
}

Someone playing with the system however will have it return to the first response on the 4th try. So you can set a counter that say after X number of off topic responses, then have it either redirect to a person, or stop responding completely.

The detection part is tricker. One way to approach this is to have a single intent that detects off topic, and then use a second workspace to drill down to the related off topic. This prevents polluting your main intents, and only requires further calls when needed. I may go into more detail on this later.

For more information on how to handle off topic/chit chat and much more, I strongly recommend doing the Designing Conversational Solutions (Watson Conversation Service) training.

Using counters in Conversation.

In Watson Dialog the use of counters was pretty easy. In Conversation it is as well, but not as intuitive yet. Here I am going to explore three methods of building and using a counter.

First to create a counter, you need to go to advanced mode in your node. You can then type in something like the following.

{
  "output": {
    "text": "Keep saying T1"
  },
  "context": {
    "countdown": 3
  }
}

A common mistake that people make is to forget to add the comma after the output block. Conversation will normally make the editor window red, but doesn’t give any hints if you do this. Worse still, if you don’t notice the red block then Conversation will revert that node if you attempt to test or edit another node.

After this we create a node with the following output.

Counter is at: <? context.countdown-- ?>

This tells conversation to display the counter we made, then decrement it. Within the nodes condition we can check to ensure the counter is greater than 0, if not then move to the next node to tell them you are finished. For example:

conv-0922-4

Hiding the counter

Now you may not want the end user to be able to see the counter. In which case we need to mask the executing code from being rendered. To do this we create a node with the code to execute as follows:

<? context.countdown-- ?>

You then set this node to continue from another node, linking to the output (very important!). In the second node, you put the following into the advanced output window.

{
  "output": {
    "text": {
      "append": false,
      "values": [
        "Still counting down."
      ]
  }}}

What this does is generate output “Still counting down.”, but because “append” is false, it will erase the previous output. So the user only sees this message.

conv-0922-3

Do you really need a counter?

The simple solution can be to not use a counter at all. The following code for example will simulate the previous example by just cycling through custom responses.

{
  "output": {
    "text": {
      "values": [
        "Keep saying T3.",
        "Counting down 3",
        "Counting down 2",
        "Counting down 1",
        "Counting finished!"
      ],
      "selection_policy": "sequential"
    }
  }
}

Here is the sample conversation script you can play with.

Important reminder!

If you use the counter in your conversation flow, you should be responsible for it! It is good coding practice to declare it in the conversation.

Apart from being able to test, it allows you to see where the application layer would likely set the counter. Plus if something failed at the application layer you can trap easier.

Depending on the complexity of your conversational flow, you may sometimes want the application layer to handle modifying the counter. This is fine as well, but still initialize in conversation, even if the application overwrites that initialization.

 

Watson Virtual Agent

Just released today. This is a SaaS that sits on top of Conversation. It allows a non-developer to easily set up a chat bot using predefined intents for common issues. With the ability to have the UI all ready for you, along with detailed metrics on how users are interacting with your virtual agent.

The introduction video explains it better.

From a developer point of view, it’s business as usual. You can build more complex conversation flows, and then have those hooked into the virtual agent.

[edit] In all the excitement I forgot the link. 

https://www.ibm.com/marketplace/cloud/cognitive-customer-engagement/us/en-us

Treat me like a human.

So one of the main pitfalls in creating a conversational system is assuming that you have to answer everything, no matter how bad it is. In a real life conversation we only go so far.

If you attempt to answer every question the user stops talking and treats the conversation system more like a search engine. So it’s good to force the user to at least give enough context.

One Word

Watson intents generally don’t work great with a single word. To that end create a node with the following condition.

input.text.matches(‘^\S+$’)

This will capture the one word responses. You can then say something like: “Can you explain in more detail what it is you want?“.

Of course you can have single word domain terms. They don’t give you enough context to answer the user, but enough to help the user. For example, lets say you are making a chat bot for a Vet office. So you may set up a node like this:

conv-0919-1

You can then list 2-3 questions the user can click and respond to. For example:

1. Why does my fish call me Bob?
2. How do fish sleep?

If you do need to create a list, try to keep it to four items or under.

Two to Three Words

Two to three words can be enough for Watson to understand. But it’s possible that the person is not asking a question. They could be trying to use it like a search engine, or a statement. You may also want to capture this.

To that end you can use the following condition.

input.text.matches(‘^\S+ \S+$|^\S+ \S+ \S+$’)
AND input.text.matches(‘^((?!\?).)*$’)

This will only capture 2-3 words that do not contain a question mark.

Here is the sample conversation script.

Handling Process Flows

While stepping a user through a process flow, don’t assume that the user will ask random questions. Even if they do, you don’t have to answer them. In real life, we wouldn’t try to answer everything if we are in the middle of something.

We may answer something in context, but we are more likely to get impatient, or ask to stop doing the flow and go back to Q&A.

So when creating your flow, try to keep this in mind. If the user asks something outside of what you expect, ask again only make the answers linkable (as long as there is a limit of answers). For example:

Watson: Do you want to a cat or a dog?
User: How do fishes sleep?
Watson: I don’t understand what you mean. Did you want a cat or a dog?

If the user persists, you can create a break out function. As you do a first pass through your user testing, you can see where you need to expand out. Don’t start off coding as if you expect them to break out everywhere.

 

What is your name?

Asking a persons name in Conversation allows you to personalise responses later on. However actually getting a name from a person which looks good in personalisation is quite hard.

First thing to consider is how you ask the question. Take these examples.

  1. What is your name?
  2. Can I get your name?
  3. How do you like to be known as?

All three of these can illicit different responses from the end user, some not the name at all. Possible responses can be.

  • (1) Simon O’Doherty
  • (2) Why do you want to know my name?
  • (2) No
  • (3) Hugh Jass

None of these answers are ideal. The first one will look silly in personalisation. The next two need to be addressed. The last one is just silly.

So at this point is very important to shape what you send to the user. Actually everything you write, especially in process flow you need to be mindful of how you shape your message.

For this example we are going to use “Hello. Before we begin, can I get your name?“. This is liable to get responses as shown above about “why” and “no”. But you will also find that people will often not even read what is being said. So you could also expect a question.

To deal with this, we can create a simple entity to look for common key terms.

conv-0911-1

The reason to use an entity over intents is that in a process flow, the scope of questions is very narrow, and we don’t want to interfere with any other intent training that is required.

We can take the following actions on each entity.

@NameOptions:why
Output: “I need your name so I can be more personalised. Can I get your name?” and ask again.

@NameOptions:question
Output: “Before you ask me a question, can I get your name?” and ask again.

Don’t try to be everything to everyone!

I have seen people try to have Conversation answer any question at any time. This can cause serious issues in process flows, and make it seem more like a search engine.

When creating a process flow, don’t assume that the end user will do everything. Test with your users first to see where you need to customise behaviour.

 
@NameOptions:no
We don’t want to force the person to give their name. So we can customise this with the following advanced code:

{
    "output": {
        "text": "No problem, you don't need to tell me your name. Please ask me a question"
    },
    "context": {
        "name": ""
    }
}

We are setting the context variable name to blank, so that personalisation doesn’t have a name.

Condition: input.text != “”
This node is to actually load the persons name using the following advanced code:

{
  "output": {
    "text": "Hello <? input.text ?>. Please ask me a question."
  },
  "context": {
    "name": " <? input.text ?>"
  }
}

Condition: true
Output: “I didn’t quite get that.” and ask again.
We use this final node in case someone enters nothing. We just send back to ask again.

Here is the sample script for above.

Avoid too much personalisation!

When personalising responses, you should avoid doing it too often. Having the persons name appear infrequently has much more of an impact.

Try to create multiple possible responses and have 1 out of every 4-5 personalised and random responses.

Outstanding Issues

So while this will work, there are still a number of issues you need to factor in.

Too much information: What happens if they answer “My name is Simon O’Doherty”. Conversation cannot handle this, and will use the whole text .

To work around this, you can try passing the users input to AlchemyAPI and Entity extraction to get the persons name. Running on the text above gives the following output (truncated):

"entities": [
        {
            "type": "Person",
            "relevance": "0.33",
            "count": "2",
            "text": "Simon O'Doherty"
        }
    ]

There are still issues with this though, which you will find when you experiment with it. Another option is a simple UIMA dictionary which detects names. I did an example of this long ago, although using WEX or Watson Knowledge Studio may make it a lot easier.

gbenj8n

Bad information: Apart from the joke or offensive names, allowing the user to personalise responses means your system is open to abuse. So you will need to do some sanitisation at the application layer to stop this.

Response formatting: In the example script you will see that context name is being set by ” <? context.name ?>”. However when you test, you will see the preceding space is removed. Without this, you will get some odd formatting like “Hello .” if no name is specified. You need to correct this at the application layer.

Tools of the trade – UltraEdit

So I use a number of applications to help in building and testing Watson. But the main ones I use are as follows.

  • Ultraedit
  • SPSS Modeller
  • Excel
  • Languages: Java and Python
  • iPad (no seriously :))

I want to touch on UltraEdit for this one. I primarily use it for the following.

  • Making mass fixes to data that SPSS can’t easily handle, and languages take too long.
  • Making the JSON readable
  • Extracting meaningful data from JSON to work with.
  • Putting that data back easily.

It is a pretty powerful text editor which allows you to do very complex search/replace/modifications to data. I am of the opinion if you prefer a different text editor, then go with what you know. But here are the main scripts I use for UltraEdit.

When you open the conversation JSON file it will look a little bit like this.

conv-0907-1

Just a mess. There is two scripts I picked up from UltraEdit that allow you to decompress it and compress it back to what you see above.

JSON – readable

if (!UltraEdit.columnMode) {
if (!UltraEdit.columnMode) {if (!UltraEdit.activeDocument.isSel()) {
UltraEdit.activeDocument.selectAll();
}
var jsonText = UltraEdit.activeDocument.selection;
var json = JSON.parse(jsonText);
var jsonTextFormatted = JSON.stringify(json, null, 2);
UltraEdit.activeDocument.write(jsonTextFormatted);
}

Will turn it into this.

conv-0907-2

To turn it back again.

JSON – compress

if (!UltraEdit.columnMode) {
if (!UltraEdit.activeDocument.isSel()) {
UltraEdit.activeDocument.selectAll();
}
var jsonText = UltraEdit.activeDocument.selection;
var json = JSON.parse(jsonText);
var jsonTextFormatted = JSON.stringify(json, null, null);
UltraEdit.activeDocument.write(jsonTextFormatted);
}

Now there are purists out there that can live with reading JSON. I’m sure all they can see is blond, brunette, redheads. For me I prefer to have my data with a lot less noise.

To that end I created two macros for extracting the entities and intents from the conversation file, into a format you can open in excel/SPSS.

Conversation – get intents

if (!UltraEdit.columnMode) {
if (!UltraEdit.activeDocument.isSel()) {
UltraEdit.activeDocument.selectAll();
}
var jsonText = UltraEdit.activeDocument.selection;
var json = JSON.parse(jsonText);UltraEdit.newFile();
var intents = json.intents;UltraEdit.activeDocument.write(‘”Question”,”Intent”\n’);
for (var i = 0; i < intents.length; i++) {      var intent = intents[i].intent
var examples = intents[i].examples      for (var j = 0; j < examples.length; j++) {
UltraEdit.activeDocument.write(‘”‘ + examples[j].text + ‘”,”‘ + intent + ‘”\n’);
}}}

Creates a CSV file you can work with.

conv-0907-3

Conversation – get entities

if (!UltraEdit.columnMode) {
if (!UltraEdit.activeDocument.isSel()) {
UltraEdit.activeDocument.selectAll();
}var jsonText = UltraEdit.activeDocument.selection;
var json = JSON.parse(jsonText);UltraEdit.newFile();var entities = json.entities;
UltraEdit.activeDocument.write(‘Entity\tValue\tSynonyms\n’)
for (var i = 0; i < entities.length; i++) {var entity = entities[i].entity
var values = entities[i].valuesfor (var j = 0; j < values.length; j++) {
UltraEdit.activeDocument.write(entity + ‘\t’ + values[j].value + ‘\t’);var synonyms = values[j].synonyms
var syn = ‘ ‘
for (var k = 0; k < synonyms.length; k++) {
syn += ‘”‘ + synonyms[k] + ‘”,’
}
UltraEdit.activeDocument.write(syn + ‘\n’)
}}}

This one creates a Tabbed separated file (TSV) with the entities in a nice readable format.

conv-0907-4

I also have scripts to put the intents and entities back into the conversation script, but I don’t plan to release at this time. As it is so easy to make a mess, and I won’t be supporting these.

You can pick up the scripts here.

Handling low confidence answers in Conversation.

So I will be switching between, newbie to expert in no particular order. This post assumes you already know how to use conversation.

In earlier versions of Watson, it was designed to handle high, medium and low confidence answers in different ways. With conversation this all works a little bit differently.

For this example, I am using the NLC demo intents. The first thing you have to do is find your low confidence.

Unlike earlier versions of WEA, the confidence is relative to the number of intents you have. So the quickest way to find the lowest confidence is to send a really ambiguous word.

These are the results I get for determining temperature or conditions.

treehouse = conditions / 0.5940327076534431
goldfish = conditions / 0.5940327076534431
music = conditions / 0.5940327076534431

See a pattern? 🙂 So the low confidence level I will set at 0.6. Next is to determine the higher confidence range. You can do this by mixing intents within the same question text. It may take a few goes to get a reasonable result.

These are results from trying this (C = Conditions, T = Temperature).

hot rain = T/0.7710267712183176, C/0.22897322878168241
windy desert = C/0.8597747113239446, T/0.14022528867605547
ice wind = C/0.5940327076534431, T/0.405967292346557

I purposely left out high confidence ones. In this I am going to go with 0.8 as the high confidence level.

Once you have those, you can create your conversation. Your first node is to check that later nodes won’t fail.

conv0905-1

The next nodes check to see if a low confidence or medium confidence is hit. For low, it won’t respond. For medium, it will display text, then continue from the next condition to find the actual answer.

conv0905-2

When you test it, you get the following results.

conv0905-3

You may still need to test with users to tweak the upper value.

Using this fall through method makes it easier to maintain with your intents. You can use a nested option if only certain intents need to be hit.

Here is the Sample file.

Gotchas: When writing numbers in conditions, always start it with a numerical value like “0.8”, not “.8”. Otherwise you will get a Dialog node error: EL1049E:(pos 24): Unexpected data after ‘.’: ‘8’

Do you even need a chat bot?

With everyone rushing out to create bots, I am reminded of the Jurassic Park quote: “Your scientists were so preoccupied with whether or not they could, they didn’t stop to think if they should”. 

Despite what people will tell you, conversation or chat bots for that matter are not needed for everything.

For example where a simple web form will do, it will out perform against a chat bot. But if that same form could have most of it answered by one question, then a chat bot may be a better solution (or maybe you just need a better form).

Or simply changing your internal processes may negate the need for a chat bot. For example, imagine after analysing your support calls for training the bot you find that over 90% of calls are due to one printer. Do you create the bot, or just replace the printer?

Or if your customer knows your domain language then a search engine or Retrieve and Rank may be a better solution.

IBM normally does all this checking through what we call a Cognitive Value Assessment (CVA). A well done CVA reduces all head aches on projects. Even if you don’t go with IBM, you should realistically examine your business process to determine if you even need a chat bot, and not just jumping on the bandwagon.

Why Conversation?

Most of the chat bots out there are just messaging frameworks, that allow you as a developer to interact with existing messaging systems. How you interpret, talk, react is all handled through code.

Out of the box, where Watson Conversation excels is the ability to take a knowledge domain (ie. Customer) that doesn’t directly match your Domain knowledge. With a handful of questions you can have your conversational bot answering questions it has never seen before.

Conversation also makes it relatively easy to write out your conversational flow (also known as chat-flow & process flow, depending on how long you worked in Watson).

Conversation is meant to piggy back on existing messaging frameworks to build intelligence into them with ease.

The danger of making things easy, is that people skip the theory and go straight to the development. The older people in the audience will remember when Visual Basic (or Lotus Notes for that matter) came out. It became easy to create applications, but most were travesties in UI, maintainability and functionality.

My focus going forward is to cover more the theory end to resolve this. As I am already competing with a number of blogs + videos in relation to Conversation.

Clean Slate

It’s been a couple of years since I last touched the blog. I thought I would start from scratch. I have everything backed up in case someone is looking for something (stats say otherwise).

I thought I would focus on conversational bots, as most of my work has been in this area. Mainly Watson related though.