{"id":160,"date":"2019-10-22T23:44:52","date_gmt":"2019-10-22T23:44:52","guid":{"rendered":"http:\/\/www.alpha-quantum.com\/blog\/?p=160"},"modified":"2019-11-01T23:12:38","modified_gmt":"2019-11-01T23:12:38","slug":"dependency-parsers-in-natural-language-processing-nlp-and-computational-linguistics","status":"publish","type":"post","link":"https:\/\/www.alpha-quantum.com\/blog\/dependency-parsers\/dependency-parsers-in-natural-language-processing-nlp-and-computational-linguistics\/","title":{"rendered":"Dependency parsers in Natural Language Processing (NLP) and Computational Linguistics"},"content":{"rendered":"

Dependency parsers are tools that allow us to analyze sentences, with particular focus on their grammatical structure.<\/p>\n

As evidenced by their name, dependency parsers allow us to parse<\/strong> the sentences and find the dependencies<\/strong>.<\/p>\n

When analyzing and parsing the sentences, dependency parsers are looking for the so-called “head” words. In analyzing dependencies, they show how those head words depend on other words and in particular, how other words “change” or “modify” the head words.<\/p>\n

To illustrate this let us use the open source library spacy<\/a>. Spacy is versatile in many NLP tasks and it also includes an excellent dependency parser (you may also check out the other state of the art tool in this field – Stanford CoreNLP).<\/p>\n

If we apply spacy dependency parsing on the sentence “They are driving fast”, we get the following nice diagram:<\/p>\n

 <\/p>\n

 <\/p>\n

\"\"<\/p>\n

The outgoing arrows indicate that the word “fast” modifies the word driving with the nature of their relation described by special tags, in this case advmod.<\/p>\n

Some of other modifiers are:<\/p>\n