Skip to main content

NLP in Search Engine Optimization





In the earlier days of search engines, the major focus was on keywords and detection of these keywords across web pages. But in recent times, the focus has shifted from keywords based searches to conversational and relevancy measures.

Today, search engines like Google are not only focusing on matching the exact keywords given in the search query but to find the order of "relevancy" of the query. The idea is that if the engine understands what the query is about then the search results will not only match those web pages which contain the exact search query but also semantically same text which may be relevant to the query.

use of NLP in search engines makes getting the exact answer to the search query and easy task and resolves the amount of clutter a user has to go through to find the relevant material. NLP makes the search engine honour context of the query and its relation to the previous query.

Voice search is also responsible for the change in dynamics of Search engines.
The search queries from Voice search and from traditional textual search differ vastly in the structure and the results wanted.

This is more related to the task of Natural Language Understanding (NLU) which is a subset of NLP.
Two methodologies used for this task are finding the relevancy and Latent Semantic Indexing (LSI).
In this blog, I am going to introduce how the relevancy is modelled.

 GloVe is an NLP algorithm developed in Stanford.

"GloVe is an unsupervised learning algorithm for obtaining vector representations for words. Training is performed on aggregated global word-word co-occurrence statistics from a corpus, and the resulting representations showcase interesting linear substructures of the word vector space."

it converts words to their vector representations along with the measures of co-occurrences. GloVe uses Nearest neighbours and Linear substructures. Nearest neighbours provide a metric to reveal an effective measure of rare but relevant words. for example, a frog can be is relevant (related) to words like frogs, toad, Litoria, Leptodactylidae, rana, lizard, eleutherodactylus.
Linear substructure differentiating between words
Linear substructure provides the measure to accurately distinguish between two words, the simple estimate is the vector difference between the two words.

Word vector representation for seo
vector representation of "Seo"

GloVe vectors allow us to measure the similarity or the differences in words. Using which we can find the set of similar words which can then be used in search engines.


Similarity terms for dui lawyer

The above words are not necessarily related to "dui lawyer" but their relevancy is high in that one is likely to encounter these words in context of "dui lawyer".

representation in terms of vectors allows another advantage. We can manipulate words as vectors and in the same way we can do operations on these vectors.

Adding and subtracting vectors
The above image represents that the GloVe vector for Queen is very closely similar to that of King - Man and Women. This is beneficial for SEO as we can approximately obtain new words to search for using vector operations.

Conclusion:
NLP, even though a relatively newer entrant in search engines is already very powerful in modelling how to decompose a query and find relevant answers. Google HummingBird update deeply integrates NLP and NLU in the search algorithm and is already providing a better search experience. With supervised learning, relevancy measure, LSI and LDA, NLP is expected to completely overhaul the scenario of search and SEO in the coming years.


REFERENCES:
https://nlp.stanford.edu/projects/glove/
http://searchengineland.com/word-vectors-implication-seo-258599
https://contentequalsmoney.com/natural-language-the-next-big-thing-in-seo/
http://www.searchengineworkshops.com/articles/lsi-and-nlp-truths.html

Comments

Post a Comment

Popular posts from this blog

NLP in Video Games

From the last few decades, NLP (Natural Language Processing) has obtained a high level of success in the field  of Computer Science, Artificial Intelligence and Computational Logistics. NLP can also be used in video games, in fact, it is very interesting to use NLP in video games, as we can see games like Serious Games includes Communication aspects. In video games, the communication includes linguistic information that is passed either through spoken content or written content. Now the question is why and where can we use NLP in video games?  There are some games that are related to pedagogy or teaching (Serious Games). So, NLP can be used in these games to achieve these objectives in the real sense. In other games, one can use the speech control using NLP so that the player can play the game by concentrating only on visuals rather on I/O. These things at last increases the realism of the game. Hence, this is the reason for using NLP in games.  We ...
4 comments
Read more

Discourse Analysis

NLP makes machine to understand human language but we are facing issues like word ambiguity, sarcastic sentiments analysis and many more. One of the issue is to predict correctly relation between words like " Patrick went to the club on last Friday. He met Richard ." Here, ' He' refers to 'Patrick'. This kind of issue makes Discourse analysis one of the important applications of Natural Language Processing. What is Discourse Analysis ? The word discourse in linguistic terms means language in use. Discourse analysis may be defined as the process of performing text or language analysis, which involves text interpretation and knowing the social interactions. Discourse analysis may involve dealing with morphemes, n-grams, tenses, verbal aspects, page layouts, and so on. It is often used to refer to the analysis of conversations or verbal discourse. It is useful for performing tasks, like A naphora Resolution (AR) , Named Entity Recognition (NE...
5 comments
Read more

Word embeddings and an application in SMT

We all are aware of (not so) recent advancements in word representation, such as Word2Vec, GloVe etc. for various NLP tasks. Let's try to dig a little deeper of how they work, and why they are so helpful! The basics, what is a Word vector? We need a mathematical way of representing words so as to process them. We call this representation, a word vector. This representation can be as simple as a one-hot encoded vector having the size of the vocabulary.  For ex, if we had 3 words in our vocabulary {man, woman, child}, we can generate word vectors in the following manner Man : {0, 0, 1} Woman : {0, 1, 0} Child : {1, 0, 0} Such an encoding cannot be used to for any meaningful comparisons, other than checking for equality. In vectors such as Word2Vec, a word is represented as a distribution over some dimensions. Each word is assigned some particular weight for each of the dimensions. Picking up the previous example, this time the vectors can be as following (assuming a 2 dime...
1 comment
Read more