1. Home
  2. Kore.ai Conversational Platform
  3. Bot Builder Tool
  4. Natural Language Processing (NLP) Optimization
  5. Managing Ignore Words and Field Memory

Managing Ignore Words and Field Memory

Developers can include words for the NLP engine to ignore when interpreting the user input for a task. Bots can then respond faster to user input and improve the probability of correct task recognition. The NLP engine comes pre-built with a large set of generic ignore words. Click the Ignore Words & Field Memory tab on the Natural language window to open the settings.

You can edit each task to persist data for that task to pre-populate in another related task for the same bot in the Field Memory settings for each task. For example, for a theme park bot, Get Wait Times for Rides task, you can pre-populate task fields into the related task, Book a FastPass action task. You can also configure words to ignore in the user input at the task level, for example, for the 7-day Weather Forecast task, you might want days of the week, such as Monday, Tuesday, and so forth, to be ignored since all weekdays are included. More…

Click a task name to show task fields that can be configured or edited for Field Memory and other field settings. To define ignore words for a task, hover your mouse over the task, and then click Edit icon.

Editing a Task

To modify, or add a configuration for a task, hover your mouse over the name of the task, and then click Edit. The Edit Task dialog is displayed.

  • Turn Off Confirmation Messages – Select Yes to disable confirmation of the execution of a task when using NLP. When No is selected, the user is asked to confirm the task before running it. For more information, see the Natural Language Processing Guide.
  • Ignore Words – Enter one or more ignore words for the task name. The list of words to ignore is processed by the Bots Platform before interpreting the user input. This means the bot can respond faster to user input and provide the correct task by filtering out words that apply to many tasks but do not help to identify which task. For example, a user may input, I want to get the weather forecast for today. To return the correct task to the user, the Bots Platform interpreter only needs to recognize three words, weather, forecast, and today. The rest of the words can be ignored. The Kore.ai Bots interpreter is already defined with a set of generic ignore words, so words like I, you, want, get, etc., do not need to be defined as ignore words. If your Bot uses the same words for many or all tasks, for example, your company name, you might add your company name as an ignore word.

Click Save to save the settings and close the Edit Task dialog.

Defining Field Memory for a Task

To add or edit Field Memory settings for a task, click the Task Name to display the associated Task Fields, and then click the Edit  icon to display the Field Memory dialog as shown in the following illustration.

In the Field Memory dialog, you can specify the following options:

  • Entity Type – Select the type of data that the NLP interpreter should expect as input to enhance recognition and performance:
    • Address - Captures addresses written in the standard US and Germany address formats, for example, 200 E Main ST Pheonix AZ 85123 USA. The complete address is captured as a string: “200 E Main ST Pheonix AZ 85123 USA.” For other country addresses, the platform captures strings that end with a recognizable city or country name. For more details, refer to the City entity.
      "entities": 
      {
      "AddressEntity": "200 E Main ST Pheonix AZ 85123 USA"
      }
    • Airport - Captures airport details with the following inputs: city name, airport name, IATA code, ICAO, or abbreviations of US cities. Airport details are returned as JSON entity with the elements shown below:
      "AirportEntity": 
      {"IATA": "LHR", 
      "AirportName": "London Heathrow Airport", 
      "City": "London", 
      "ICAO": "EGLL", 
      "Latitude": "51.4775", "Longitude": "-0.461389" 
      }
      We use https://github.com/opentraveldata/opentraveldata for all the airport details.
      Input Description Examples
      City name Identifies the airport name from the city name in the user utterance. If the city has multiple airports, shows the list of airports to choose from. Learn about City entity. Utterance: Flying to Los Angeles Response: The airport you entered seems to be ambiguous. Tell me the option you would like to choose. <Names of five airports in Los Angeles>
      Airport name Identifies the airport name from full airport name or partial name with the prominent keyword. Utterance: Flying to Heathrow Captured: London Heathrow Airport with the necessary details in the bot.
      IATA Identifies airport names by the International Air Transport Association (IATA) codes. Utterance: Flying to LHR Captured: Details of the London Heathrow Airport
      ICAO Identifies International Civil Aviation Organization (ICAO) codes. Utterance: Flying to EGLL Captured: Details of the London Heathrow Airport
      Abbreviations of cities Identifies city abbreviations that are listed in www.geonames.org Utterance: Flying to LA Response: The airport you entered seems to be ambiguous. Tell me the option you would like to choose. <Names of five airports in LA>
    • Attachment(Image / File) - The user can attach a file, image, or email of up to 25 MB. The bot returns the attachment description that you enter as a string.
      "entities": 
      {
      "AttachmentEntity": "send"
      }
    • City - The name of a city in an utterance such as What is the temperature in New York. The bot captures any city name with over 5000 population in the form of a string. We use www.geonames.org for all the city details.
      Note: City names are not disambiguated currently but prioritized based on their population. So, if the user utterances consist of Portland, Portland OR ranks higher than Portland ME.
      "entities": 
      {
      "CityEntity": "New York"
      }
    • Company Name or Organization Name - Captures the name of a company from user utterances such as Nearest branch for Amazon. The value for Company Name is returned (Amazon) as a string. See Supported Companies list. Apart from the supported companies, the bot recognizes the words starting with a capital letter and followed by these suffixes as a company type: Inc, Incorporated, Corp, Corporation, Group, Ltd, Limited, Co, Company, LP, LLP, LLLP, LLC, PLLC.
       "entities": 
      {
      "OrganizationEntity": "amazon"
      }
    • Color - Captures the name of the of a color from a user utterance, for example, Set the status to green. Returns the value for Color as green as a string. See Supported Colors list.
      "entities": 
      {
      "ColorEntity": "green"
      }
    • Currency - Captures the amount and type of currency from the user utterance, for example, This handbag is priced at 200 dollars, where 200 is the amount and USD is the currency. Recognizes Full currency names (Dollar, Rupees, Indian national rupees, Dinar), Currency symbols ($, S$, £), standard currency abbreviations (INR, USD), and commonly used slang for currencies,(Buck, Nickel, Dime, Quid, Loonie, Toonie, Benjamin, Jackson, Hamilton.)
      Note: Currency names are not disambiguated based on your previous usage. So, if the user utterance consists of a dollar first time, USD might rank higher than SGD (Singapore Dollar) because of the popularity. But if the user explicitly mentions SGD, the bot continues to consider SGD for the dollar from there.
      "CurrencyEntity":[
      {
      "code": "SGD",
      "amount": 20
      }
    • Custom - Define a regular expression to validate the user input in the Regex field displayed. For example, enter: [a-zA-Z]{3}[-]\d{4} to return a sample response as {"regex":"NLP-1234"} For more information, see Regex Expressions.
    • Composite - Composite entities can be used to capture multiple entity values in one entity. For example, consider the sales inquiries to car sales. Typical queries can be of the form: ‘I am interested in Tesla Model S 2018 model’ or ‘What would a red Tesla 2010 model cost’ or ‘Tell me about Tesla Model S’. As you can see, the bot typically needs to process a combination of details like Make, Model, Year and Color to respond to those queries. Refer here to know more about Composite Entity Types.
    • Date - Captures a date mention from a user utterance, for example, Book a flight on the 10th of October. Returns the value for Date in ISO8601 date format as YYYY-MM-DD. The bot recognizes all possible ways and formats of dates, for example, these:
        • YYYY-MM-DD
        • DD-MM-YYYY
        • DD-MM-YY
        • 1 Jan 1982 or 1st Jan.
        • This day last year
        • Next Friday
        Note: If a task already has calculated a date via a previous entity, then the relative date is based on that date, not the current date. Missing elements of a date expression are auto-filled, for example, if the utterance just includes Feb 20, the year is automatically filled.
      "entities": 
      {
      "DateEntity": "1982-04-13"
      }
    • Date Time - Captures a date grouping along with a time in a user utterance, for example, Book a flight on the 10th of October at 6 pm. Returns the value for Date Time in ISO8601 date format as YYYYY-MM-DDThh: mm: ss.sTZD. The bot recognizes all possible ways and formats of expressing dates and time.
      "entities": 
      {
      "DateEntity": "2017-10-10T18:00:00+05:30"
      }
    • Date Period - Captures start date and end date from the user input, for example, Book the hotel for five days starting May 5. If the user input doesn’t include one or both of the dates, the bot prompts the user to provide the necessary input.
      Note: Unlike other entities, Date Period entities allow you to enter two sets of user and errors prompts:
      1. User and Error Prompts for From Date
      2. User and Error Prompts for To Date
      The following table lists how the entity works in different scenarios:
      Input Type Bot Behaviour
      Doesn’t include both From and To dates [e.g., Book hotel] Shows User Prompts for From Date to the user
      Includes either From or To date [e.g., Book a hotel from 15th Aug] Shows User Prompts for From Date or User Prompts for To Date based on which is missing from the input
      Includes implicit reference to From Date and duration [e.g., Book a hotel for five days starting from Tuesday] Determines both dates
      Includes From Date and duration [e.g., Book a hotel for five days from 15th Nov] Determines both dates
      Includes From Date and To Date [e.g., Book a hotel from 5th to 10th] Determines both dates
    • Description - Captures statements or paragraphs of text from the user utterance. The value for Description is returned as a string and can include wild characters.
      Note: Is Multi-Item is not available for this entity type.
      "entities": 
      {
      "DateEntity": "2017-10-10T18:00:00+05:30"
      }
    • Email - Captures email address from the utterance, for example, Send an email to help@koremessenger.com. Returns the value of Email as a string.
      "entities": 
      {
      "Email": "help@koremessenger.com"
      }
    • From number (minimum of a range) - Captures the beginning number of a number range from a user utterance, for example, Not available for ages 18 to 21, where 18 is the value for From number. The bot recognizes the numbers in words also, for example, if the user utterance consists of “Starting from five”, 5 is taken as the From number.
      Note: Is Multi-Item is not available for this entity type.
      "entities": 
      {
      "From": "5"
      }
    • List of Items (enumerated) - Display a list of values to the end-user. To define the list type, click the Settings icon located to the immediate right of the Type field to open the List of items (enumerated) Setup page to define one of the following list types.
      • Static List - Enter the Display Name for the key, the Value for the key, and optionally, enter synonyms for the key. Set up Auto Correction value for the user inputs.
      • List from context - Define a context variable to use for this item in the following fields:
          • Specify Context Variable to Use - Defines the context object type, for example, EnterpriseContext, BotContext, UserContexts, or session variables such as context.entities. Enter context., and then select a context object type.
          • Display Name Key - The name displayed to the end user.
          • Value Key - The key that represents the value of the item in the list.
          • Synonyms Key - Enter one or more synonyms for the key.
        • Auto Correction- Set up auto-correct thresholds for the LOV entity type so that it not only accepts exact matches but also closest utterances with small variations. For example, let’s consider that a list value called Apple for which a typo such as “appel” could be accepted based on your threshold settings. The Auto-Correction setting works in the following way:
          1. The bot identifies the number of letters to be changed (inserts, deletes or replaces) in user input to match it to a value in the list
          2. The number is converted to a percentage of the total number of letters in the input
          3. The list value with the highest similarity is considered as input if the score is greater than or equal to the configured percentage.
          Spell correction doesn't apply to dictionary words or alphanumeric inputs.
    • List of items (lookup) - Display a list of values to the end-user. To define the lookup list, click the Settings icon located to the immediate right of the Type field to open the List of items (lookup) Setup page to define the entity values as one of the following list types:
      • JSON tab - Enter a list of key/value pairs and synonyms, for example:
        [{
        "title": "United States",
        "value": "US",
        "synonyms": ["united states", "USA", "US", "U.S.A", "America"]
        },
        {
        "title": "John F. Kennedy International Airport",
        "value": "JFK",
        "synonyms": ["John F. Kennedy International Airport", "New York International Airport", "JFK"]
        }
        ]
      • Editor tab - Enter the Display Name for the key, the Value for the key, and optionally, enter Synonyms for the key.
      • Upload File - Click to navigate to and select a JSON formatted file list, or a .csv file formatted list of key/value pairs, for example, CSV File Format
    • Location - Captures the location details of a city or state from a user utterance. For example, in Bellagio, Las Vegas the entity captures the location details of Las Vegas. The entity returns the location of the object with address and coordinates as a JSON response.
      "Location": 
      {
      "formatted_address": "Las Vegas, NV, USA",
      "lat": 36.1699412,
      "lng": -115.1398296
      }
    • Number - - Captures a number from a user utterance, for example, Book a room for 16 people. In this example, the value 16 is returned as the Number. Bots Platform recognizes the spelled out numbers and also standard abbreviations such as 1M. Consecutive number words are combined into one number, for example, one two three becomes 123.
      "entities": 
      {
      "NumberEntity": 16
      }
    • Person Name - Captures the full name of a person from a user utterance, for example, Send an email to John Smith. where John Smith is identified as Person Name. Kore.ai Bot Platform comes inherently with most popular names. If a name is missing in the list, it assumes that the first word in the user utterance with capital letters as the first name along and the next two words in camel case as a part of the name. For example, if the user utterance is “I want to talk to John Smith,” it recognizes John Smith as the name. If the utterance is “I want to talk to John immediately” it recognizes only John as the name.
      "entities": 
      {
      "PersonName": "John Smith"
      }
    • Percentage - Captures the percentage value from a user utterance, for example, The chance of rain today is more than 60 percent, where 60 is the Percentage. and returned as a float value of 0.6 in a range of (0.0-1.0). Supports percent, percentage, and the % sign.
      "entities": 
      {
      "PercentageEntity": 0.6
      }
    • Phone Number - Captures standard 10-digit or 12-digit telephone numbers, for example, Please call 4075551212. The value for Phone Number is 4075551212 and is returned as a number.
      "entities": 
      {
      "PhoneNumber": "+919177776716"
      }
    • Quantity - Captures the quantity in an utterance with the following details: Type of the quantity (length, area, volume etc.), unit of measurement (kilometers, square kilometer, cubic meter etc.), the amount (100, 500, 1.5 etc.) from the user utterance. When you select Quantity entity type, you also need to select a unit type for the quantity and the default measure. For example, for capturing volumes, select Volume as the Unity type and Milliliters as the Default unit. So, if a user utterance is Add 500 ml of water, the following JSON is returned
      "Quantity": 
      {
      "unit": "millilitre",
      "amount": 500,
      "type": "volume",
      "source": "500 ml"
      }
      .Bots platform identifies all these quantities and unites along with the standard abbreviations, codes, and symbols.
      • Length - Select one of the following default units of length.
        • kilometer
        • meter
        • centimeter
        • inch
        • foot
        • yard
        • mile
      • Area - Select one of the following default units of area.
        • square kilometer
        • square meter
        • square mile
        • square yard
        • square foot
      • Volume - Select one of the following default units of volume.
        • cubic meter
        • liter
        • milliliter
        • gallon
        • ounce
      • Time - Select one of the following default units of time.
        • hour
        • minute
        • second
        • millisecond
      • Speed - Select one of the following default units of speed.
        • meters per second
        • kilometers per hour
        • miles per hour
      • Pressure - Select one of the following default units of pressure.
        • pascal
        • atmosphere
        • bar
      • Energy - Select one of the following default units of energy.
        • calorie
        • kilocalorie
        • watt-hour
        • kilowatt hour
      • Memory - Select one of the following default units of memory.
        • bit
        • byte
        • kilobyte
        • megabyte
        • terabyte
        • gigabyte
      • Weight - Select one of the following default units of weight.
        • ton
        • kilogram
        • gram
        • pound
        • ounce
      • Angle - Select one of the following default units of angle.
        • degree
      • Age - Select one of the following default units of age.
        • Day
        • Week
        • Month
        • Year
        • Decade
        • Century
      • Temperature- Select one of the following default units of temperature.
        • celsius
        • fahrenheit
    • String - Works identically to the Description entity.
    • Time - Capture time in a user utterance, for example, Set my alarm for 6 am. Returns the value of Time in ISO 8601 time format as Thh:mm:ss.sZD. It recognizes the following denotations:
        • am, a.m., AM, pm, p.m., PM, P.M.
        • Numbers spelled out, for example, Six AM.
        • Morning and evening, for example, Six in the evening.
      "entities": 
      {
      "TimeEntity": "T06:00:00+05:30"
      }
    • Time Zone - A time zone, for example, Eastern standard time. Converts the timezone into GMT and stores the resulting value. For example, if you type EST, it is stored as -6:00. Bots Platform recognizes the standard time zones in this list.
      "entities": 
      {
      "TimeZoneEntity": "-06:00"
      }
    • To number (maximum of a range) - Captures the ending number of a number range, for example, Not available for ages 18 to 21, where 21 is the value for To number. The bot recognizes the numbers in words also, for example, if the user utterance consists of “Ending with ten”, 10 is taken as the To number.
      Note: Is Multi-Item is not available for this entity type.
      "entities": 
      {
      "ToEntity": "10"
      }
    • URL - Captures a web URL from the utterance, for example, Vist our website: www.kore.ai. The bot recognizes all standard formats of URLs. The value for URL is returned as a string.
      "entities": 
      {
      "URLEntity": "www.kore.ai"
      }
    • Zip Code - Captures a US zip code from the user utterance, for example, What is the weather for 32746? The value for Zip Code is 32746 and is returned as a string.
      "entities": 
      {
      "ZipcodeEntity": "32746"
      }
  • Memory User Provided Value – Enable or disable persistence of data provided by the user for a specified time. One of:
    • No, do not memorize – The user’s data for this field is not persisted after the task is completed.
    • Yes, memorize this value – The field value is persisted for the time specified in minutes.

Click Save to save the settings and close the Field Memory dialog.

Next Steps

To collect all of the information required for a task, the NLP interpreter must be able to recognize what task the user wants and collect the parameter values of the task fields. To optimize NLP interpreter recognition, you can add synonyms and patterns for words or phrases used in the names of your bot task or task fields. For more information, see the Managing Synonyms and the Managing Patterns.

To learn more about best practices and tips for optimizing NLP, see the Natural Language Processing Guide.

Was this article helpful to you? Yes 1 No