Everything you need to know
Computers don’t speak languages the way humans do. They communicate in machine code or machine language, while we speak English, Dutch, French or some other human language. Most of us don’t understand the millions of zeros and ones computers communicate in. And in turn, computers don’t understand human language unless they are programmed to do so. That’s where natural language processing (NLP) comes in.
What is natural language processing?
Natural language processing is a form of artificial intelligence (AI) that gives computers the ability to read, understand and interpret human language. It helps computers measure sentiment and determine which parts of human language are important. For computers, this is an extremely difficult thing to do because of the large amount of unstructured data, the lack of formal rules and the absence of real-world context or intent.
In recent years, AI has evolved rapidly, and with that, NLP got more sophisticated, too. Many of us already use NLP daily without realising it. You’ve probably used at least one of the following tools:
- Spell checker.
- Spam filters.
- Voice text messaging.
Five basic NLP tasks
As we mentioned before, human language is extremely complex and diverse. That’s why natural language processing includes many techniques to interpret it, ranging from statistical and machine learning methods to rules-based and algorithmic approaches. There are five basic NLP tasks that you might recognise from school.
Part of speech tagging
One of the tasks of NLP is speech tagging. For every sentence, the part of speech for each word is determined. Part of speech is a category of words that have similar grammatical properties. For example, the word book is a noun in the sentence the book on the table, but it’s a verb in the sentence to book a flight. And a word like set can even be a noun, verb or an adjective.
There is a large number of words that can serve as multiple parts of speech, which makes it challenging for a machine to assign them the correct tags.
Lemmatisation concerns removing inflectional endings only and reducing a word to its base form, which is also known as a “lemma”. Past tenses are changed into present and synonyms are unified. For example, the past tense ran is changed to run and the synonym best is unified into good.
Lemmatisation uses a different approach than stemming to reach the root form of a word. For example, the lemma of caring is care, not car as it is with stemming.
The tokenisation task cuts a text into smaller pieces called tokens. This process segments a chunk of continuous text into separate sentences and words, while at the same time removing certain characters, like punctuation. For example, this sentence split up into smaller tokens would look like this:
For example this sentence split up into smaller tokens would look like this
That pretty much looks the same, right? That’s because languages like English often separate words with a blank space, but not all languages do. In those languages, tokenisation is a significant undertaking that requires deep knowledge of the vocabulary.
In English, too, blank spaces may break up words that actually should be considered one token. Think of city names like Los Angeles or San Francisco or the phrase “New York-based”.
Disambiguation is a task that has to do with the meaning of the words we use in human language. Some words have more than one meaning, and while reading, we select the meaning that makes the most sense in the given context. For example, the word bat can refer to the animal that flies around at night or the wooden or metal club that is used in baseball. And a bank can be a place where you go to open a current account or a piece of land alongside a body of water where you go fishing.
Humans communicate based on meaning and context. Semantics help computers identify the structure of sentences and the most relevant elements of a text in order to understand the topic that is being discussed. For example, if a text contains words like election, democrat and republican or budget, taxes and inflation, the computer understands that the topics discussed are American politics and economics.
Examples of natural language processing in practice
In recent years, because of the availability of big data, powerful computing and enhanced algorithms, natural language processing has been rapidly advancing and transforming businesses. It’s now widely used across an array of industries. We have listed some interesting examples below:
- NLP is widely used in the translation industry. Many localisation companies use machine translation to help their translators work more efficiently. When the text is already largely translated by machine, it saves them valuable time and the number of words they can translate daily increases.
- Search engines use natural language processing to come up with relevant search results based on similar search behaviour or user intent. By using NLP, the average person finds what they’re looking for.
- NLP is also used for email filters. The spam filter has been around for quite some time now, but Gmail’s email classification is one of the newer NLP applications. Based on the content of the emails that come in, Gmail now also recognises to which of the three categories (primary, social or promotions) the emails belong. This helps users determine which emails are important and need a quick response, and which emails they probably want to delete.
- We also see the use of natural language processing in healthcare. It can be used for streamlining patient information or for apps that convert sign language into text. The latter enables deaf people to communicate with people who don’t know how to use sign language.
- NLP is even being used in the aircraft maintenance industry. It helps mechanics find useful information from aircraft manuals that have hundreds of pages, and it helps find meaning in the descriptions of problems reported by pilots or others working in the industry.
Ways we use NLP at Textmetrics
What the examples above show is that there are numerous ways that NLP can improve how your company operates. That’s because human interaction is the driving force of most businesses. When you’re not too familiar with AI and NLP, though, it can be quite challenging to do it right. And having employees manually analyse all of the content that your company produces is almost impossible.
At Textmetrics, we offer a number of tools that use natural language processing to help organisations analyse their content and provide suggestions for improvements.
- A spell checker enables everyone in your organisation to create grammatically correct and error-free content.
- A tool to determine the language level of the content you’ve created. This is based on the European Language Framework.
- A tool to flag words that are gender-biased, providing suggestions and possible replacements based on the target audience you’re creating the content for.
- An algorithm-based program based on the needs of your organisation to help you standardise your communication according to your corporate identity.
Are you curious to know more about these tools, or do you want to find out if they could be of use in your organisation? Please let us know. Textmetrics is here to help!
When you’re browsing the web or developing a website, you probably don’t realize that there are groups of people who struggle with the accessibility of digital information on a daily basis. Among these are people with a physical disability, photosensitive seizures, and cognitive disabilities. You could also think of older people with a growing visual or hearing impairment. To make sure that these people can access digital information just as well as all other users can, a number of guidelines have been prepared. These guidelines are known as the WCAG, the Web Content Accessibility Guidelines.
Four important principles of the WCAG
The guidelines of the WCAG are based on the following four principles:
People should be able to use and experience the website with the senses that they have available. Some web users may have difficulties with one or more of their senses. Therefore, they might need assistive technology to browse your website.
Means to make your website perceivable:
- Use textual alternatives for non-textual content.
- Provide a transcript for audio and video content.
- Add subtitles to videos
People should be able to use and find the content on the website, regardless of the way they use your website. Some users might have motor difficulties and use their keyboard to navigate, while others who have a sight impairment will often use a keyboard instead of a mouse.
Means to make your website operable:
- Ensure good keyboard-only navigation.
- Avoid setting time limits for users.
- Use descriptive links so people know where they lead to.
People should be able to understand the software and your website, and they should understand how the website works. Your website can only be perceivable and operable if it’s understandable. So make sure your website functions in a way that everyone can understand.
Means to make your website understandable:
- Give the software the ability to decide on the language of the page.
- Make sure the content is readable and understandable.
- Make sure that forms have visible and meaningful labels.
The content on your website should enable reliable interpretation by a wide range of user agents. It should run on third-party technology (like web browsers) that people can rely on. This way you avoid the risk that users relying on technology cannot correctly access your website.
Means to make your website robust:
- Use error-free code.
- Ensure maximum compatibility with current and future browsers.
- Make sure that third-party technologies understand what each function is for.
Accessibility is important for all users
Accessibility is not only crucial for users with a disability of some sort. Other users, or we should say ALL users, benefit from a website that is accessible. If your website and web content live up to the principles we mentioned above, then the overall user experience and satisfaction of users will improve. Some features that were once designed for users with a specific disability are now often used by others as well. Situations you could think of are:
- You want to watch a video but you’re in a room with a lot of noise and there is no way that you’re ever going to hear what the people in the video are saying. In that scenario, you are grateful that the video is subtitled, so you can watch it anyway.
- Or you’re working from home and the weather is just lovely so you decide to work outside for a little while, but the sun is so bright that it’s harder to see what’s on your screen. Then it’s good to know that the contrast of the colors on the website are enhanced so the content is easier to read.
Why accessibility is important for your company
There are a number of reasons why accessibility is important for your company. We have outlined the most important reasons below:
- You don’t want to exclude anyone.
It should be the company’s top priority to make sure that its website is accessible to as many people as possible. Why should you exclude people when it’s not that difficult to implement the Web Content Accessibility Guidelines? Accessibility is key to reaching your entire target group. The bigger your audience, the more traffic and conversions your website will generate.
- Your market reach will increase.
The market of people with disabilities and the aging population is large and keeps on growing. In the Netherlands, for example, an estimated 25% of the population has some form of disability. If you make sure that your web content is accessible and well-received by ALL users, you can extend your market reach. Especially across different devices and in a variety of situations.
- Greater customer satisfaction.
Usability and customer satisfaction go hand in hand. Updating your website design according to the Web Content Accessibility Guidelines, also improves its usability. That’s because web accessibility is also beneficial in these situations:
- When people browse your website on devices like mobile phones, smartwatches, and other devices with small screens.
- When people suffer temporary disabilities, like a broken arm or lost glasses.
- When people browse your website in challenging situations, like bright, glaring sunlight.
- When people browse your website using a slow internet connection.
How Textmetrics can help you with the accessibility of your web content
At Textmetrics, we have a number of tools that can help you improve the accessibility of your website and web content. First of all, you can use one of our tools to scan a web page or crawl your entire website for elements that do not comply with the Web Content Accessibility Guidelines. For instance, our tool flags elements where the contrast of the colors is not up to par, where text scaling or zooming is not available, or where there is no text alternative for an image. Once you know what the issues are and how your website can be improved, it’s easy to implement the necessary changes.
This is important in order to reach your entire target group and to adhere to your company’s Inclusion and Diversity Policy. Recruitment departments often struggle with inclusion when it comes to job openings. Our tool can help recruiters write job ads that appeal to everyone. Together with our Gender Scan, which lets you know if your content has a more male or female tone of voice, Textmetrics facilitates a giant leap forward when it comes to inclusion.
Want to see whether you are excluding people in your (web) communication? Use our Website Inclusion Check to find out.
For more information on how to use our Accessibility feature, check out this article.
Textmetrics launches WordPress Plugin update with structured data feature for Google for Jobs.
Our new WordPress Plugin update will allow you to add job information in your WordPress website in such a way that it can be processed by Google, so that your jobs can be indexed and appear in the Google Search results.
What is Google for Jobs?
It’s an enhanced search feature that was released by Google in the US in July 2017 and has since gone live in almost every part of the world. Now that it’s made available, it’s vital that you adapt to the shift in order to use Google Jobs to your benefit. It’ll assist job seekers to find vacancies that closely match their preferences. They can easily search and apply to open vacancies directly from the Google search bar. This tool is designed to improve the recruitment process for job seekers and employers alike.
How Does It Work for Job Seekers and Employers?
Like every other Google creation, it works in the simplest way. When you search for jobs using the Google jobs search tool, you’ll view job vacancies at the top of the search results. It has various filters to help you narrow down your searches, such as experience, job specialities, qualifications, working hours, salary, and more. You can then click through to see the job descriptions and apply to the positions right from Google for Jobs.
As an employer, you are unable to post jobs directly with Google for Jobs as it retrieves jobs from multiple jobs sites such as Monster, Glassdoor, LinkedIn, etc. To enable Google for Jobs to index your job postings, you will need to add job postings structured data (also known as schema markup) to your careers page. Adding structured data makes your job postings eligible to appear in a special user experience in Google Search results. Structured data communicates to search engines what your data means. Without it, search engines can only tell what your data says, and they have to work harder to determine why it’s there. The required data includes:
- Date – date of the job posted
- Organization – the company offering the job position
- Job description – such as qualification, required skills, working hours, responsibilities… etc
- Job Location – where the job seeker will be working from
- Title of the job
Now, this is where Textmetrics’ latest WordPress update will benefit employers. The WordPress plugin will (automatically) generate Schema.org structured data for the “Job Posting” type. In the plugin settings, you can provide default Organization data (i.e. name, logo or location data). This new feature makes it easier for employers to index their job postings on Google for Jobs.
Why Use it?
It enables both job seekers and employers to connect in the easiest way possible. You will not only see the job posting with the exact job title, but you’ll also be able to find positions that match your preferences. This way, you won’t have to look for the right job by searching for different keywords as Google will present similar job postings to you. You no longer have to hop from one platform to another just to find your dream job – as Google for Jobs will be doing that for you. By making full use of this platform, recruiters will be able to get an influx of job seekers that fit their requirements and needed skills. This will reduce the time of going through candidates who are unsuitable for the jobs that they have posted.
Are you ready to have your job postings indexed and easily found by your next potential candidate through Google for Jobs? Let us help you achieve this goal! At Textmetrics, we use AI to enable you to create specific and unique target group content. Our tools are based on scientifically proven algorithms and help you monitor the quality of your content.
Technological developments, like automation and robotizing, are about to change the workforce of the future. Current jobs will disappear, there will be new roles that we haven’t even heard of yet, and people working at companies will need new skills to do their jobs. What is the impact of all these changes on the recruitment strategies of companies? Although companies know these changes are upon them and HR professionals are aware that things are already shifting, it seems that most companies are not prepared to handle the consequences of automation just yet. In short, they are not prepared for the workforce of the future. Why is that? And what should companies be preparing for?
The cold, hard facts
Jobs will cease to exist due to technological developments. This is something we know for sure. In fact, 90% of HR professionals have said that they are already noticing the consequences of increased automation. Almost three-quarters of all jobs are changing when it comes to the daily requirements of the role. And over 30% of HR professionals say that new jobs have emerged due to automation.
It’s not only HR professionals who are aware that this is happening. Many employees are experiencing the increasing impact of automation on their jobs. In fact, it has a huge impact on them. Research into HR trends revealed that in 41% of the organizations studied, jobs have disappeared due to automation, and in 71% of the organizations, jobs have changed for the same reason.
Impact on people
That automation has an impact on people’s jobs is something HR professionals are aware of. However, it seems that they are not aware of the impact it has on the people who are working in those roles. What are the impacts of these changes to staffing levels, competences, recruitment, the need for education and work processes?
Research shows that people are aware that their jobs are changing and want to keep up with these changes. However, the companies they work for rarely offer them the opportunity to pursue further education. Instead, they receive little support from HR. This is something companies and HR professionals should pay increasing attention to in the years to come. It would be a shame to see a lot of people lose their jobs simply because they missed out on the training required to keep up with the changes that automation brings.
How are the jobs of HR professionals changing?
Automation changes the jobs of HR professionals, too. There are new and innovative technologies that can take care of many of the time-consuming tasks involved in recruitment, making them much more time-efficient. When new jobs appear due to technological developments, you might need to hire new staff to fill these positions. That’s not always easy. There are more positions to fill, but most of the time, the number of recruiters to fill them does not increase. On top of that, these positions can be difficult to fill because they are so new, and it’s possible that there aren’t very many people who are qualified for them. This is where automation—and artificial intelligence, in particular—comes in and can help recruiters work faster and more effectively.
At Textmetrics, we offer a solution that enables organizations to create target group-specific and corporate-wide consistent content using augmented, assisted writing based on scientifically proven algorithms. This means that recruiters can use them to create job posts that attract the right target group, even if this is a group that is hard to find. More people will apply, making the time required for the recruitment process shorter. On top of that, the tools make it easier to write according to company standards, ensuring that all job posts are consistent in language use and readability. Last but not least, the job post can be easily optimized for SEO, guaranteeing that people searching for a job online are able to find your job ad.
Are you ready to implement automation in your HR department? Textmetrics is here to help you in your recruiting process, with real-time SEO suggestions and content that leads to conversions!