API usage

Why API

NLPBuddy supports an API which you call and take advantage of the following features:

1. Language identification (performed using langid library).
2. Text tokenization.
3. Sentence splitting.
4. Lemmatization.
5. Part of Speech tags identification.
6. Named Entity Recognition (Location, Person, Organization).
7. Text summarization (uses Gensim's implementation of the TextRank algorithm).
8. Keywords extraction.
9. For the Greek language:
   • Text classification among the following categories: Sports, Science, World News, Greek News, Environment, Politics, Art, Health, Science. The Greek classifier is built with FastText and is trained in 20.000 articles labeled in these categories. Accuracy reaches 90%,
   • Text subjectivity analysis.
   • Emotion analysis. It detects the main text emotion among the following emotions: Anger, Disgust, Fear, Happiness, Sadness, Surprise.
10. Lexical Attributes.
11. Noun chunks.

Our goal is to provide all these functionalities with a single API call so anybody can use NLPBuddy for any purpose that fits his needs.

API usage

This section provides an example call to the API and a sample response.

Example:

user@user~$ curl -H "Content-Type: application/json" -XPOST --data '{"text": "Indonesia earthquake: 14 dead on tourist island of Lombok.A powerful earthquake has struck a popular tourist destination in Indonesia, killing at least 14 people."}' https://nlpbuddy.io/api/analyze

Or in python

import requests
url = 'https://nlp.wordgames.gr/api/analyze'
text = """
Indonesia earthquake: 14 dead on tourist island of Lombok.
A powerful earthquake has struck a popular tourist destination in Indonesia, killing at least 14 people."
"""
res = requests.post(url, json={'text': text})
res.json()

Example response:

{"language": "English", "named_entities": {"person": [], "organization": ["Lombok"], "location": ["Indonesia"]}, "part_of_speech": {"verbs": ["has", "struck", "killing"], "adjectives": ["dead", "powerful", "popular"], "nouns": ["earthquake", "tourist", "island", "destination", "people"]}, "lemmatized_sentences": ["indonesia earthquake : 14 dead on tourist island of lombok .", "a powerful earthquake have strike a popular tourist destination in indonesia , kill at least 14 people ."], "lexical_attrs": {"emails": [], "urls": [], "nums": ["14", "14"]}, "sentences": ["Indonesia earthquake: 14 dead on tourist island of Lombok.", "A powerful earthquake has struck a popular tourist destination in Indonesia, killing at least 14 people."], "keywords": "indonesia, earthquake, tourist, powerful, kill, strike, popular, people, lombok, dead", "noun_chunks": ["tourist island", "Lombok", "A powerful earthquake", "a popular tourist destination", "Indonesia", "at least 14 people"], "text": "<span class=\"tooltip\" data-content=\"POS: PROPN<br> LEMMA: indonesia<br> DEP: compound\" style=\"color: red;\" >Indonesia </span><span class=\"tooltip\" data-content=\"POS: NOUN<br> LEMMA: earthquake<br> DEP: dep\" >earthquake </span><span class=\"tooltip\" data-content=\"POS: PUNCT<br> LEMMA: :<br> DEP: punct\" >: </span><span class=\"tooltip\" data-content=\"POS: NUM<br> LEMMA: 14<br> DEP: nummod\" style=\"color: red;\" >14 </span><span class=\"tooltip\" data-content=\"POS: ADJ<br> LEMMA: dead<br> DEP: ROOT\" >dead </span><span class=\"tooltip\" data-content=\"POS: ADP<br> LEMMA: on<br> DEP: prep\" >on </span><span class=\"tooltip\" data-content=\"POS: NOUN<br> LEMMA: tourist<br> DEP: compound\" >tourist </span><span class=\"tooltip\" data-content=\"POS: NOUN<br> LEMMA: island<br> DEP: pobj\" >island </span><span class=\"tooltip\" data-content=\"POS: ADP<br> LEMMA: of<br> DEP: prep\" >of </span><span class=\"tooltip\" data-content=\"POS: PROPN<br> LEMMA: lombok<br> DEP: pobj\" style=\"color: red;\" >Lombok </span><span class=\"tooltip\" data-content=\"POS: PUNCT<br> LEMMA: .<br> DEP: punct\" >. </span><span class=\"tooltip\" data-content=\"POS: DET<br> LEMMA: a<br> DEP: det\" >A </span><span class=\"tooltip\" data-content=\"POS: ADJ<br> LEMMA: powerful<br> DEP: amod\" >powerful </span><span class=\"tooltip\" data-content=\"POS: NOUN<br> LEMMA: earthquake<br> DEP: nsubj\" >earthquake </span><span class=\"tooltip\" data-content=\"POS: VERB<br> LEMMA: have<br> DEP: aux\" >has </span><span class=\"tooltip\" data-content=\"POS: VERB<br> LEMMA: strike<br> DEP: ROOT\" >struck </span><span class=\"tooltip\" data-content=\"POS: DET<br> LEMMA: a<br> DEP: det\" >a </span><span class=\"tooltip\" data-content=\"POS: ADJ<br> LEMMA: popular<br> DEP: amod\" >popular </span><span class=\"tooltip\" data-content=\"POS: NOUN<br> LEMMA: tourist<br> DEP: compound\" >tourist </span><span class=\"tooltip\" data-content=\"POS: NOUN<br> LEMMA: destination<br> DEP: dobj\" >destination </span><span class=\"tooltip\" data-content=\"POS: ADP<br> LEMMA: in<br> DEP: prep\" >in </span><span class=\"tooltip\" data-content=\"POS: PROPN<br> LEMMA: indonesia<br> DEP: pobj\" style=\"color: red;\" >Indonesia </span><span class=\"tooltip\" data-content=\"POS: PUNCT<br> LEMMA: ,<br> DEP: punct\" >, </span><span class=\"tooltip\" data-content=\"POS: VERB<br> LEMMA: kill<br> DEP: advcl\" >killing </span><span class=\"tooltip\" data-content=\"POS: ADV<br> LEMMA: at<br> DEP: advmod\" style=\"color: red;\" >at </span><span class=\"tooltip\" data-content=\"POS: ADV<br> LEMMA: least<br> DEP: advmod\" style=\"color: red;\" >least </span><span class=\"tooltip\" data-content=\"POS: NUM<br> LEMMA: 14<br> DEP: nummod\" style=\"color: red;\" >14 </span><span class=\"tooltip\" data-content=\"POS: NOUN<br> LEMMA: people<br> DEP: dobj\" >people </span><span class=\"tooltip\" data-content=\"POS: PUNCT<br> LEMMA: .<br> DEP: punct\" >. </span>", "text_tokenized": ["Indonesia", "earthquake", ":", "14", "dead", "on", "tourist", "island", "of", "Lombok", ".", "A", "powerful", "earthquake", "has", "struck", "a", "popular", "tourist", "destination", "in", "Indonesia", ",", "killing", "at", "least", "14", "people", "."], "summary": ""}