Ever since discovering Karen Spärck Jones and learning more about her, I’ve been reading a lot about information retrieval and natural language processing – especially as it relates to search engines. As I researched, I started to wonder about other languages. What about search engines for people who solely speak Spanish? Hindi? French? And even Russian! Are there gaps in efficiency & quality of these search engines compared to those in English, the world’s most widely spoken language? And if so, do any languages suffer more, and why?
I dug a bit more into widely used Russian search engines, out of curiosity. Apparently, the three most widely used ones are Yandex, Google.ru, and Rambler, listed in order of their popularity. I’ll focus on Yandex (or Яндекс, in Russian) in particular.
Founded in the 1980s by CEO Arkady Volozh, much before even Google was founded, Yandex (short for “yet another indexer” of the Runet, or Russian internet) is thought to have the truly “superior search technology,” according to this Forbes article. This is because Yandex’s search algorithm is specifically suited to account for the nuances in the Russian language. For instance, Russian has around 20 different endings that words can take on to indicate their relationship with other words in phrases and sentences. All Russian nouns also have grammatical “gender,” in a sense, and this can affect other words in sentences. For instance, in the sentence “Рея моя новая друг” (Rhea is my new friend), моя (my) and новая (new) are in their feminine forms, while in “Александр мой новый друг” (Aleksandr is my new friend), мой (my) and новый (new) are in their masculine forms.
This makes Russian an extremely precise language, which is good – but it makes search very difficult. While Google.ru will search for the exact word combination you have entered in the search bar (i.e. only documents with your 1 ending, out of the 20 possible, will show up, limiting your search results), Yandex manages to parse words down to their stems (like Spärck Jones proposed!), to include all 20 possible endings for all words in question, and therefore is better at bringing up documents that account for true user intent. Super cool, right!
Yandex controls 56% of the Russian search market, as a result, while Google holds 23%. It’s undoubtedly favored by Russians, and with good reason. In addition to its novel search algorithm, the broader company also offers Yandex.Mail (free email, like Gmail), live traffic maps through Yandex.Maps (especially useful in major cities like Moscow, St. Petersburg, and Kiev), and more. The traffic maps were pretty fun to play around with!
So from now on, I think I’ll be using Yandex to handle my search queries whenever I feel like searching in Russian. I hope this post has inspired you to do so as well!
Счастливого Яндексинга! (Happy Yandexing!) 🙂