

Get monthly notifications
Why does Siri not understand me? AI and language comprehension
One of the challenges that researchers face in Artificial Intelligence (AI) is being able to understand human language and simulate it through technology.
Think of the following situation: you ask for help from Google Assistant, Siri, Alexa or any other artificial assistant and the result you get is far from what you wanted to express. There are times that, depending on the way we speak or the words we write, are very difficult for personal assistants to understand, therefore, it is essential that the AI becomes more skillful when it comes to understanding the human language.
Google has always been concerned with improving that understanding gap in its searches, so today we want to talk to you about how smart systems work through the example of SyntaxNet and its analyzer, Parsey McParseface.
Can you imagine being able to build an application that understands human language? This is the project presented by Google in 2016, which consists of a model of neural networks with open source from which any developer can develop applications linked to natural language.
Wow...! But how does it work?
SyntaxNet with its analyzer, Parsey McParseface, combines automatic learning and search techniques to improve the learning of English and use the language with an accuracy of 94%, according to Google.
For us, humans, speaking is very easy. In fact, we do not think about it, and we only begin to notice that our linguistic system must be quite complicated when we face the task of learning a second or third... languages.
Humans learn to speak from the time they are children, increasing their vocabulary, modifying the meaning and restrictions and intentions of words and adapting the relevance of the words to use in different contexts. We learn from those who are close to us (from the context) and we understand more and more vocabulary (semantics) and structure (syntax) almost effortlessly.
Something similar happens with AI systems, although it is much more difficult to artificially encode all the complexity of human reasoning, since all truths are approximate and encounter many obstacles along the way; for example, the large number of meanings that a word can have or the intention of a sentence in a certain context.
Let's see how SyntaxNet works in the following example:
Given a sentence as input, the processor labels each word with a speech part label, which describes the syntactic function of the word and determines the syntactic relationships between the words in the sentence.
These syntactic relationships are directly related to the meaning of the sentence:
This structure codes that Alice and Bob are nouns and Saw is a verb. The main verb saw is the root of the sentence and Alice is the subject (NSubj) of saw, while Bob is its direct object (DObj).
As you can see, Parsey McParseface analyzes this sentence correctly, but let's see what happens in a more complex example:
Any human can understand this phrase and imagine Alice driving a car down the street. But an AI system may be able to understand what for a human being would be an absurdity: that Alice is driving having the street inside her car. This is one of the main problems that makes the analysis so challenging: human languages show remarkable levels of ambiguity.
Human beings do remarkable work in dealing with ambiguity, almost to the point where the problem is imperceptible. The challenge is creating computers that are capable of doing the same.
SyntaxNet applies neural networks to the problem of ambiguity. Instead of simply taking the first decision at each point, multiple partial hypotheses are maintained at each step, and the hypotheses are only discarded when there are other hypotheses of greater rank under consideration.
The main source of errors at this point are examples such as the previous sentence, which requires knowledge of the real world (for example, that a street is not likely to be located in a car) and also deep contextual reasoning.
Machine learning (and, in particular, neural networks) has made significant progress in resolving these ambiguities; and, while the precision is not perfect, it is certainly high enough to be useful in many applications.
This is just one example of how investigations into AI are trying to improve intelligent systems: understanding the meanings and launching a better hypothesis every time. A great goal, right? And, thinking of how voice Search will affect digital marketing, the challenge increases. Here’s a look at 6 ways voice search will impact digital marketing:
-
Complexity will increase: queries are much complex than they were even 3 years ago due to largely to changes in Search Engine Algorithms that have become less attuned to keywords and more capable of inferring meaning.
-
Interactions will be shorter: people are usually run out of time, this is why quick interactions regarding needs, answers to usual questions… will dominate the communication between humans and assistants.
-
Local search will rise: related to the previous point, shorter interactions are usually used for local things, such as, find the close restaurant, fastest way to go to somewhere… Many voice searches happen on the go.
-
Audio-only interactions will increase: it will be a change in the way of information is presenting. Focusing more on the meaning and the value of the action, rather than images, infographics, and other visual media.
-
Challenge to attain top ranking. Digital assistants only return the top result based on your “voice-search query”, you may not be able to view the lower rankings of possibilities.
-
Conversational content will be important, such as semantics, pragmatics and the impact of content, situations and intentions. It will expect a conversational, human answer in return.
Surely we are closer to the day when it will be very easy to have an informal and natural conversation with our personal assistants. What is not in the slightest doubt, is that with these small-big steps, we have tools at our service, and free access, that bring us closer to an increasingly human Artificial Intelligence.
What about you? How do you live the experience of having conversations with chatbots, personal assistants, answerphones...?
More info: Announcing SyntaxNet: The World’s Most Accurate Parser Goes Open Source
How does Google use natural language processing to reduce the time to insights.
Featured Articles
Top eCommerce Predictions and Trends for 2023
The eCommerce industry is constantly evolving, especially with the advancement in tech in recent years and it can be challenging to keep up with the latest trends and technologies. In this article, we'll be forecasting some of the most exciting eCommerce trends for 2023. Knowing about these trends will help you can stay ahead of the curve and understand what the future holds for online shopping. From continued growth of mobile eCommerce to the rise of social media eCommerce, these are the trends and technologies that are expected to shape the eCommerce landscape in the coming years. Keep reading to learn more!
Google Analytics 4, Privacy and Black Week
Want to move a step ahead in getting closer to your customers? Get hold of Google Analytics 4, a gem for all businesses.
The e-commerce universe is now prepping up for the year’s extravagant fancy sale i.e., Black Week! This is where your privacy game will come into play while customers would be busy browsing lakhs of websites during this shopping spree.
Let us learn more about Google Analytics 4 and Privacy in this blog to accelerate your revenue safely.
Similar Articles
Take Your TikTok Ads to the Next Level
To look into the future, let us peep into the past once. TikTok earlier was loaded with content focused on dancing and lip-syncing videos inclined more towards an uprising for polished platforms and enabling easy access and non-positionality of content consisting of short videos largely.
Top eCommerce Predictions and Trends for 2023
The eCommerce industry is constantly evolving, especially with the advancement in tech in recent years and it can be challenging to keep up with the latest trends and technologies. In this article, we'll be forecasting some of the most exciting eCommerce trends for 2023. Knowing about these trends will help you can stay ahead of the curve and understand what the future holds for online shopping. From continued growth of mobile eCommerce to the rise of social media eCommerce, these are the trends and technologies that are expected to shape the eCommerce landscape in the coming years. Keep reading to learn more!
All About TikTok SEO 2023
INTRODUCTION
We are in the middle of an ongoing search evolution that is gradually happening! TikTok is arguably becoming a search engine, which has been recently acknowledged by Google too.
Why You Should Get Started with TikTok Ads Today?
Amazon and HBO have spent huge money on TikTok advertisements in the U.S. during the months of January and May 2022, says Statista!
And why not? TikTok reached the “1 billion” count on its daily active users in 2022! Hence, advertising on TikTok is just inescapable!
TikTok Ads are booming because their widely diversified audience has helped brands gain high profits with natural virality.
Create Successful Holiday Ads on Facebook & Instagram
Did you know? According to AdMaven, holiday retail sales have reached a whopping $789.4 billion in the year 2021!
It's the holiday season! Everyone right now is on a shopping spree and this is the time, businesses have to be on their toes. If you are not playing with your Facebook and Instagram right now, you are at a big loss in this game of Holiday Ads!
Let us begin by jumping into some holiday insights for the year 2022. Interestingly, shopkeepers have been receptive to trying out new brands across various niches this time round.
Peak Season 2022
How to Solve Privacy for Marketers & eCommerce?
The privacy-first approach is now the eligibility for a business to sustain itself in the current cutthroat competition. It is believably impractical to process a transaction without publicizing your personal information!
So, let us look for a solution and learn how to solve privacy for marketers & eCommerce in this blog.
Google Analytics 4, Privacy and Black Week
Want to move a step ahead in getting closer to your customers? Get hold of Google Analytics 4, a gem for all businesses.
The e-commerce universe is now prepping up for the year’s extravagant fancy sale i.e., Black Week! This is where your privacy game will come into play while customers would be busy browsing lakhs of websites during this shopping spree.
Let us learn more about Google Analytics 4 and Privacy in this blog to accelerate your revenue safely.
Latest Instagram Updates! [July 2022]
We’re thrilled to learn about the new features being rolled out by Instagram and we think they’re going to be a game changer for marketers and creators. These much-awaited updates were finally announced on 21 July by Adam Mosseri, the head of Instagram, on various social media platforms. Keep reading to know all about the updates.
Instagram Influencer Marketplace: The Next Big IG Update for Brands
87% of its users say influencers have inspired them to make a purchase, and 70% of shopping enthusiasts visit Instagram to discover their next purchase. Brands report Instagram influencer marketing ROI is over 5X: $5.20 for every $1 spent on influencer marketing on Instagram. That’s why Instagram has finally decided to launch an Influencer Marketplace and it’s going to be amazing for you - whether you’re a brand or an influencer. Stick with us to know what you can expect from the all-new Influencer Marketplace.
TikTok Statistics – June 2022
Spoiler Alert: this will be a text and data-heavy blog post!
TikTok is available in over 150 countries, has over 1 billion users, and has been downloaded over 9 million times in the Nordics alone. If your brand’s target audience includes anyone between the ages of 13 and 60, you should be on TikTok right now.