Articles & Showcase

A place to read & write articles as well as showcase work done with the core expert.ai technology

  • 13 Topics
  • 3 Replies

13 Topics

triyockbpo
triyockbpoNew Participant
posted in Articles & Showcase

Challenges and solution to changing Market research Industry

Utilizing a range of methods for collecting qualitative or quantitative market research data Traditional research methods are causing problems for the market research sector. Artificial Intelligence (AI) and machine learning are entering practically every aspect of life, hence the demand for development extends beyond research approaches. Outsource Data Management Services for market research data collection have specialists in using innovative and proven methods of online research and data mining to acquire data. The first phase in the market research process is data collection. Market research agencies of all sizes are continuously on the lookout for Outsource Data Management Solutions for qualitative and quantitative market research. It will enable them to move beyond static, reactive market research operations and provide consumers with real-time insights.Some challenges of market research data management: 1. Increasing the value of dataAccessing quality and representative data fro

0
triyockbpo
5 months ago
femanuele
femanueleEmployee
posted in Articles & Showcase

The Role of Intelligent Process Automation in 2022

To casual observers, technological innovation is a fast-paced environment where every other day seems to bring something entirely new to the market. Which is true, to an extent. For decades we’ve registered growing amounts of capital poured into young ventures whose only objective is to revolutionize the way we do things, processing power has grown exponentially as have the ubiquity of computers and Internet connectivity. All of this inevitably leads to thousands of startups that fight for the spotlight through improved ways to solve ordinary problems.On the other hand, for those working in this field the pace of things is much slower. A tech professional can easily spot a product that’s not truly pushing the envelope, or when a marketing message is the only original concept behind a brand. The large majority of everyday launches don’t add anything revolutionary to the mix, but they do offer something tangible: an increasingly clearer view of the underlying subject most technology prov

0
femanuele
9 months ago
femanuele
femanueleEmployee
posted in Articles & Showcase

Machine Learning’s Sweet Spot: 5 scenarios for a pure ML approach in NLP and Document Analysis

Machine Learning is slowly but surely leaving academic circles and enthusiasts’ nighttime projects to relocate to business applications. While some solutions have quickly adopted modern ML-based algorithms (Deep Learning) successfully, image recognition for example, others have been struggling with achieving production-grade results, leading to stark statistics highlighting that 85% of ML projects in major corporations never see the light of day. This is a defining step for ML as a whole, since the expectations companies have when onboarding a new technology are high, there’s a demand for higher quality than what one usually chases in a lab, and a positive return on investment is considered the norm.Nevertheless, experiments in this field are the new normal for actors in all industries. And when ML is applied to Document Analysis, some conclusions are fairly common. In fact, one in particular: that is, wondering if ML is even the best fit for a solution that requires understanding lang

0
femanuele
10 months ago
vvilla
vvillaEmployee
posted in Articles & Showcase

Check Your Biases - Symbolic Engines and Unexpected Results

AbstractBack in June 2016, only days before the Brexit vote, I was flying from Aberdeen Scotland on a British Airways plane, heading back to Italy after the K-Drive Project had just wrapped. I was carrying a laptop with me, containing a small NLP model I had developed over the past weeks to predict the Brexit outcome. Together with the model, I had the infographics detailing the prediction itself, which was uncomfortably different from the mainstream one. The K-Drive Project, under the umbrella of the Marie Curie actions, is a European funded project based at the University of Aberdeen, aimed at bringing together industry and academia, for mutual exchange and joint effort in the field of semantic technologies. I joined it as a MER (More Experienced Researcher) in January 2016, when the main paper was already being published, so I was assigned with training and public speaking tasks to showcase the NLP technology involved.During the final month leading to the end of the project, we deci

0
vvilla
10 months ago
femanuele
femanueleEmployee
posted in Articles & Showcase

AI and Natural Language Processing: State of Affairs in the Industry

With a market size in the billions and a double-digit projected yearly growth (some say 20% CAGR for the foreseeable future), NLP is not the niche it once was. We moved from looking for single words in a file to analyzing communication as a whole: at document level, at library level, at Internet level. Our scope went from one sentence on a page to twitter trends and global patterns. Today many companies base their entire marketing strategies on what people say on social media, and they’re able to track all this digital chatter thanks to Text Analytics technology. In fact, new companies and an entire industry were born just to satisfy this need for knowledge.We now face increasing complexity and strenuous demand for new tools coming from every imaginable industry; this landscape, naturally, requires technologies that become more sophisticated by the minute. We started with a straightforward approach which was revolving around key words; then this evolved into something better when we ad

0
femanuele
10 months ago
sreitano
sreitanoEmployee
posted in Articles & Showcase

Insurance Policies: Document Clustering through Hybrid NLP

Insurance Policies: Document Clustering through Hybrid NLP Insurance documents and policies: a complex use caseIt is common knowledge that up to 87% of data science projects fail to go from Proof of Concept to production; NLP projects for the Insurance domain make no exception. On the contrary, they must overcome several hardships which are inevitably connected to this space and its intricacies.The most known difficulties come from:the complex layout of Insurance-related documents the lack of sizeable corpora with related annotations.The complexity of the layout is so great that the exact same linguistic concept can greatly change its meaning and value depending on where it is placed in a document.Let’s look at a simple example: if we try to build an engine to identify the presence or absence of a “Terrorism” coverage in a policy, we will have to assign a different value whether it is placed in:The Sub-limit section of the Declaration Page. The “Exclusion” chapter of the policy. An End

1
femanuele
10 months ago
femanuele
femanueleEmployee
posted in Articles & Showcase

The Word “word” Has 13 Meanings

Thoughts around Knowledge Graphs, the semantic nature of language, and the two main types of word ambiguity. Depending on the dictionary you use to look this up, the word “word” can have 13 meanings or more, but no matter the final count (or why one dictionary would be different than another…), what is certain is that the total number isn’t 1. It’d be really hard for us to understand what people are saying if we were to take words just for what they are, words. A word carries meaning, and this meaning is different based on the context for that word. Ultimately, meaning is what matters, words are just a vehicle.Linguists, NLP (Natural Language Processing) practitioners, developers and even search engines users, they are all somewhat aware of the concept of “word ambiguity” (polysemy). You look for “beds” and in your search results you do find beds (the ones we sleep in) but also flowerbeds and other types of beds. Cases like this one are only minimally annoying because the more frequent

0
femanuele
10 months ago
lgorrieri
lgorrieriEmployee
posted in Articles & Showcase

Can you trust your model when data shifts?

In real-case applications, machine learning is not as common as we would expect: let’s explore why.Photo by Alice Yamamura on UnsplashRead the article on Towards Data Science. Machine Learning is the talk of the town. Models have shown that with today’s technology they are capable of achieving jaw-dropping results. Unfortunately, the lab and the real world are two different playfields: Algorithms work great if the data they see is similar to the ones they were trained on, but this is not always the case. Data can shift due to a number of factors:Scarcity of labeled data — annotating data is expensive, so the model is trained on what’s available hoping that it fully represents the use case; Time — e.g. new terms emerge in a language, previous facts are no longer valid, etc.; Geography — e.g. British vs American English, native vs non-native speakers, etc.; Format — e.g. short documents vs larger ones, jargon from one domain vs another domain, etc.Generalizing is the real challenge we fa

0
lgorrieri
1 year ago
femanuele
femanueleEmployee
posted in Articles & Showcase

A quick word on Hybrid AI in Natural Language Processing: the new approach to Machine Learning applied to Text Analysis

 Any solution aimed at processing unstructured data (i.e., language, specifically text in most cases) is today based on one of two main approaches: Machine Learning and Symbolic. Both can be delivered in multiple ways (different algorithms in the case of ML, from shallow linguistics to semantic technology in the case of Symbolic), but not much has been done so far in the realm of hybrid approaches. While choosing one over the other is always going to present a compromise between advantages and drawbacks (higher accuracy coming from Symbolic, more flexibility derived from ML), Hybrid AI—or Hybrid NL—is a revolutionary path to solve linguistic challenges that can leverage the best of both worlds and, ultimately, make your NLP practices graduate to NLU (Natural Language Understanding). I won’t spend time on explaining how ML or Symbolic work since there’s a ton of literature about that already, I’ll focus this page on Hybrid instead.  To frame this conversation in a practical fashion, we

0
femanuele
1 year ago
femanuele
femanueleEmployee
posted in Articles & Showcase

On Knowledge Graphs and how they enhance Natural Language Understanding technology

We’ve stepped into a second phase for Machine Learning, one in which it’s become fairly known that it isn’t very efficient to build a basic understanding of language in a Machine Learning model from scratch every time a new project starts. Language is an established baseline of every document, and it has nothing to do with the specificity of an industry or a use case. A small portion of it is, but, for the most part, a document is full of words and concepts any person would understand, even those that don’t work in the industry the text is meant for.by Jayarathina - Own work, CC BY-SA 4.0, https://commons.wikimedia.org/w/index.php?curid=37135596Therefore, it is faster to infuse the training of a model with pre-established knowledge, and the best way to do this is to adopt a knowledge graph. This new level of maturity in the AI world has rendered the conversation around knowledge graphs more common than it used to be. Consequently, now many are wondering what a knowledge graph is, how i

0
femanuele
1 year ago
femanuele
femanueleEmployee
posted in Articles & Showcase

Precision and Recall, F-score and Accuracy – Measuring NLP performance

When discussing Artificial Intelligence and Natural Language Processing, we often hear mention of Precision, Recall, F-score, Accuracy. These are ways to measure the quality of a software which returns information about an analyzed document.These same scoring systems can also be used to assess the performance of other technologies, for instance search engines, since the ultimate goal is to quantify on a percentage scale their ability to retrieve the desired data.Let’s jump into a slightly more in-depth definition for each one of these, before addressing the most important point, that is why they’re relevant.Precision: Given a set of results out of a processed document, Precision is the percentage value indicating how many of those results are correct (correct being based on the expectations of a certain application). It can apply to any class of a predictive AI system, like Search, Categorization, Entity Recognition, etc. Example: given a document mentioning 10 dog breeds and an applic

0
femanuele
1 year ago
G
gdellacorteEmployee
posted in Articles & Showcase

Landing an entry-level job in the NLP/NLU industry

Natural Language Processing Career Path: Knowledge Engineer, Computational Linguist, Speech Technologist, NLP Scientist… what job position to look for after graduation? Photo by Franki Chamaki on Unsplash If you are reading this article, the chances you are graduating in the Natural Language Processing or Computational Linguistics domain are significantly high. You are probably looking for an internship or a junior position in the NLP area. And this is exactly what I had to go through a couple of years ago. And you are probably asking yourself: What kind of career to pursue in the Natural Language Processing and/or Computational Linguistics industry? The honest answer is… it depends. Rather than focusing exclusively on a set of skills needed, I believe that to carefully choose a career path in the NLP industry, you shall ask yourself the following questions:a) What do I enjoy and like the most within the options the NLP job market can currently offer?b) What NLP related skills I curren

0
G
1 year ago
femanuele
femanueleEmployee
posted in Articles & Showcase

NLP FEATURES THAT ARE CRIMINALLY OVERLOOKED: The case for SAO

In reading of Natural Language Processing (NLP) applications, we inevitably encounter two main features in action, Categorization and Extraction, and learn how those can be manipulated in so many different ways to effectively address use cases that involve free-form text and the retrieval of information from it. We also hear a lot about Sentiment (which technically is not a separate feature but rather a specialization of the previous two). Finally, we have POS-tagging, which is only occasionally mentioned outside of deeply technical articles for linguists and NLP professionals. We don’t hear much about other NLP capabilities, and this is mainly because often, depending on how an NLP engine is designed, features beyond Categorization and Extraction are not present at all. Specifically, many NLP solutions today are based on Machine Learning algorithms, and ML rarely delivers great accuracy in problems that require both elevated precision and super-fine identification. Then again, some of

2
W
1 year ago

Badge winners

Show all badges
Terms & ConditionsCookie settings