language-engineering

from nltk.tokenize import word_tokenize
from nltk import pos_tag
from sussex_nltk.parse import dep_parse_sentences_arceager

sentences = ["This is the first example sentence",
             "This is the second example sentence",
             "This is the third example sentence"]

parsed_sents = dep_parse_sentences_arceager(pos_tag(word_tokenize(sentence)) for sentence in sentences)

language-engineering

from sussex_nltk.parse import load_parsed_example_sentences

parsed_example_sentences = load_parsed_example_sentences()
 
# To inspect the sentences, you could print them straight out
for parsed_sentence in parsed_example_sentences:
    print "--- Sentence ---"
    print parsed_sentence

language-engineering

Input:
    query_token = The token we're interested in. It is part of a dependency tree of tokens.
    
Output:
    opinions = An array of token forms (which constitute the extracted opinions related to the query token
    
opinions = []
for each dependent token of query_token, then
    append dependent's form to opinions array if the dependency relation of the dependent is "det"
    

language-engineering

def opinion_extractor(aspect_token, parsed_sentence):
    
    # Your function will have 3 steps:
    
    # i. Initialise a list of opinions
    opinions = []
    
    # ii. Find opinions (as an example we get all the dependants of the aspect token that have the relation "det")
    opinions += [dependant.form for dependant in parsed_sentence.get_dependants(aspect_token) if dependant.deprel == "det"]
    # You can continue to add to "opinions". Remember you can get the head of a token, and filter by PoS tag or Deprel too!

language-engineering

from sussex_nltk.parse import load_parsed_dvd_sentences, load_parsed_example_sentences

aspect = "plot"   # Set this to the aspect token you're interested in
save_file_path = r"/path/to/savefile.txt"    # Set this to the location of the file you wish to create/overwrite with the saved output.

# Tracking these numbers will allow us to see what proportion of sentences we discovered features in
sentences_with_discovered_features = 0  # Number of sentences we discovered features in
total_sentences = 0  # Total number of sentences 

# This is a "with statement", it invokes a context manager, which handles the opening and closing of resources (like files)

language-engineering

# Say for example we acquire a list of BasicToken objects by getting all the dependants of a token:
dependants = parsed_sentence.get_dependants(aspect_token)

# We could filter that list, keeping only those tokens whose dependency relations with the aspect token are "dobj", by doing the following:
dependants = [token for token in dependants if token.deprel == "dobj"] 

# Or we could filter that list, keeping only those tokens whose PoS tags are "RB" (for adverb)
dependants = [token for token in dependants if token.pos == "RB"]

# Or we could filter that list, keeping only those tokens whose form is NOT "main" or "special"

language-engineering

# Given a ParsedSentence object, and an aspect token acquired from it (as in the previous section)
# Get the head of the aspect token

head_token = parsed_sentence.get_head(aspect_token)
print head_token

language-engineering

# Given a ParsedSentence object, and an aspect token acquired from it (as in the previous section)
# Get all of the dependants of that aspect token.
dependants = parsed_sentence.get_dependants(aspect_token)

# You could print them out for inspection
for dependant in dependants:
    print dependant

language-engineering

aspect = "dialogue"

# If you have a ParsedSentence object, you can get all the tokens whose form matches the aspect as shown below.
# So instead of just printing the parsed_sentence as in the previous section, get its aspect tokens and print them.
aspect_tokens = parsed_sentence.get_query_tokens(aspect)

# You could iterate over them and print them for inspection
for aspect_token in aspect_tokens:
    print aspect_token
    

language-engineering

from sussex_nltk.parse import load_parsed_dvd_sentences

aspect = "dialogue"  # Our aspect word
parsed_sentences = load_parsed_dvd_sentences(aspect)

# To inspect the sentences, you could print them straight out
for parsed_sentence in parsed_sentences:
    print "--- Sentence ---"
    print parsed_sentence