Golden Gate Bridge shrouded in fog

Man vs. Machine: Word-Sense Disambiguation

Before finding my calling as a translator, I studied computational linguistics at Georgetown University. (Hoya Saxa!)

Computational linguistics is a branch of computer science focusing on natural language data, as opposed to numeric or structured data. Its applications can be found in technologies like speech recognition, information retrieval, and machine translation. I was most interested in information retrieval and extraction, the kind of software that could sift through megabytes of unstructured text and pull out important information (such as intelligence data) or respond to natural language questions (like a chatbot capable of competing in Turing test challenges). I wrote my Master’s thesis on a machine learning system for the temporal annotation of news text.

Yeah, pretty nerdy fun stuff. 🙂

Although I ultimately chose a different career path, I still have a lot of respect for the technology behind natural language processing. Language technology has a clear place, even in translation.

That said, there are some tasks that qualified humans will always do better. One such task is word-sense disambiguation.

What is word-sense disambiguation?

Word-sense disambiguation is the process by which the meaning of a word or phrase is clarified (or disambiguated) when multiple meanings are possible.

This is something that we, as humans, do all the time with great proficiency. We consider the context in which a word is used and then select the most suitable meaning. In translation, word-sense disambiguation is made easier with the help of reference documents and glossaries, if available. We also have our real-world domain-specific expertise to help us identify which words are true possibilities and which can simply be ruled out.

Simply put… Within the neural networks of the human brain, we’ve really got word-sense disambiguation figured out.

For computers, however, word-sense disambiguation is a colossal challenge.

Software follows an algorithm to perform word-sense disambiguation. These algorithms must explicitly consider various factors about the word or phrase to be disambiguated, including its part of speech, the domain of the text as a whole, the immediate context surrounding the word or phrase (which may or may not relate to the surrounding text), language, dialect, statistical probabilities of collocations, and so on.

Even in a best-case scenario, this is a lot of processing for a computer. What if the word is spelled incorrectly? What if the sentence contains a grammatical error that throws off the part-of-speech tagger? What if the word or phrase is used within a cultural reference, easily recognizable by a human but just another string of words to a computer?

In translation (or machine translation), subtleties of the source text, such as wordplay or running metaphors, may be lost when word-sense disambiguation is not performed properly.

So, what does this mean?

Computational linguists have made impressive advancements in tackling the challenges of natural language applications, all of which involve word-sense disambiguation on some level. Yes, even machine translation is getting better. It can be quite useful in informal situations or in providing the gist of a text when no proper translation is available.

But if you are doing business in foreign markets, trust your translations to expert translators who can preserve the richness of your company voice in your written documentation and marketing materials. Make a good impression on your potential customers, because how you communicate is a direct reflection of your company’s professionalism and brand image.


Quaint Boston intersection featuring architecture and fire escapes

Alternatives to Silicon Valley for Your North American Headquarters

Congratulations! You’re ready to establish the North American headquarters of your Europe-based business! But what city should you choose?

Silicon Valley is a natural choice. It’s filled with startups, but it’s SO EXPENSIVE! The same is can be said about New York City. Entrepreneurs need to consider a number of factors when selecting a location for their business, and cost is certainly one of them!

Thankfully, there are plenty of other attractive and more affordable cities that boast tons of tech talent and even have direct flights to and from Paris-CDG! Here are just a few of the stand-outs:


Atlanta, Georgia is enjoying lots of momentum these days, with a 21% growth in tech talent since 2010. Home of Georgia Tech and Vanderbilt University, Atlanta offers a low overall cost of living and a low cost of doing business.

Washington, DC

Known more for its lobbyists and politicians and crowded with government contractors, Washington offers loads of tech talent from its many local universities, including those in nearby Virginia and Maryland. With its prime mid-Atlantic location, Washington is home to several well-known educational companies, including Rosetta Stone and Blackboard.


No surprises here! Seattle makes this list because it is still more affordable than Silicon Valley and the Big Apple. Home to Amazon, Microsoft, Zillow, and many more tech companies, the downside to this city is that you may need to compete for talent. Each year, there is an estimated 3,000-person shortage in filling software development and engineering jobs, according to the Washington Technology Industry Association, so you’ll need to be ready to offer plenty of perks and an amazing company culture to woo prospective talent.


Home to the prestigious Harvard University and Massachusetts Institute of Technology, Boston ranks 3rd in startups and 5th in quality of life. It is also home to companies like TripAdvisor and iRobot. In terms of location, Boston is conveniently just a short drive or train ride from New York and a comfortable plane ride from Paris.


This North Carolina city is the tech hub of the Southeast. Its “Triangle” is home to a thriving startup community and tech scene. Raleigh also offers low taxes and a low cost of living, making it especially attractive to cash-strapped startup companies!


Located in Canada, just across the border from Seattle, Vancouver is the home of Hootsuite, as well as satellite offices of Facebook, Apple, and Twitter. Canada ranks among the highest standards of living in the world, easily attracting top talent, some formerly employed by Canada’s lost-but-not-forgotten export BlackBerry. Other great Canadian cities with direct flights from Paris-CDG are Toronto and French-speaking Montreal.

As you can see, North America offers lots of potential to European innovators seeking to grow! Good luck!

Old-fashioned rotary pay phone

Mr. Watson, Come Here (This Day In History – March 10, 1876)

We give very little thought these days to picking up a phone and calling anywhere in the world. Or texting. Or snapchatting. We are immensely connected to one another, a reality that has had monumental implications on our societies, economies, and more.

The world was entirely different just 140 years ago, when Alexander Graham Bell made the first ever telephone call to his assistant Thomas A. Watson, who was in the next room. (Couldn’t he just get up and walk over to his desk?!)

Bell, like several members of his family, devoted his life to the study of sound, specifically elocution, acoustics, and speech. His interest was motivated by the fact that both his mother and his wife were deaf.

In the years preceding Bell’s famous invention, telegraph communication was popular, consisting of tones transmitted via telegraph wire. However, it was clear that this form of communication would not suffice for long. From his laboratory in Boston, Bell went to work on developing a solution for transmitting sound via wire.

Initial experiments with transmitted sound produced promising, yet muffled results. To be effective, this technology would have to transmit the human voice clearly enough to be understood by someone on the receiving end.

As with many innovations, Bell was not the only inventor working to produce a feasible solution for transmitting vocal sound, but he was the first to patent the invention, issued on March 7, 1876, as U.S. patent #174,465, for “the method of, and apparatus for, transmitting vocal or other sounds telegraphically … by causing electrical undulations, similar in form to the vibrations of the air accompanying the said vocal or other sound.”

Three days later, he demonstrated a working prototype of the telephone, by calling his assistant Watson. He said, “Mr. Watson—Come here—I want to see you.”

And with that, the telephone was born!

(Curiously, Watson remembers the famous words slightly differently, as instead being “Mr. Watson – Come here – I want you,” so you could say that this was also the first game of telephone as well!)