Created
July 3, 2024 15:25
-
-
Save kristiyanto/a5d9ec70a04e11f1aef9a384db71a42a to your computer and use it in GitHub Desktop.
NLP: NER using rule based matcher - Medium Article
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| # Refer to the Jupyter Notebook and article for package imports and the complete code. | |
| def extract_keywords(text, max_keywords=10): | |
| doc = nlp(text) | |
| matcher = Matcher(nlp.vocab) | |
| # Noun and Noun Phrases | |
| noun_phrases_patterns = [ | |
| [{'POS': 'NUM'}, {'POS': 'NOUN'}], #example: 2 bedrooms | |
| [{'POS': 'ADJ', 'OP': '*'}, {'POS': 'NOUN'}], #example: beautiful house | |
| [{'POS': 'NOUN', 'OP': '+'}], #example: house | |
| ] | |
| # Geo-political entity | |
| gpe_patterns = [ | |
| [{'ENT_TYPE': 'GPE'}], #example: Tokyo | |
| ] | |
| # Location | |
| loc_patterns = [ | |
| [{'ENT_TYPE': 'LOC'}], #example: downtown | |
| ] | |
| # Facility | |
| fac_patterns = [ | |
| [{'ENT_TYPE': 'FAC'}], #example: airport | |
| ] | |
| # Proximity | |
| proximity_patterns = [ | |
| [{'POS': 'ADJ'}, {'POS': 'ADP'}, {'POS': 'NOUN', 'ENT_TYPE': 'FAC', 'OP': '?'}], # example: near airport | |
| [{'POS': 'ADJ'}, {'POS': 'ADP'}, {'POS': 'PROPN', 'ENT_TYPE': 'FAC', 'OP': '?'}] # example: near to Narita | |
| ] | |
| for entity, patterns in zip(['NOUN_PHRASE', 'GPE', 'LOC', 'FAC', "PROXIMITY"], | |
| [noun_phrases_patterns, gpe_patterns, loc_patterns, | |
| fac_patterns, proximity_patterns]): | |
| matcher.add(entity, patterns) | |
| matches = matcher(doc) | |
| keywords = [] | |
| for match_id, start, end in matches: | |
| span = doc[start:end] | |
| match_label = nlp.vocab.strings[match_id] | |
| keywords.append((match_label, span.text.strip().lower())) | |
| keyword_freq = {} | |
| for keyword in keywords: | |
| keyword_freq[keyword] = keyword_freq.get(keyword, 0) + 1 | |
| keywords = sorted(keyword_freq, key=keyword_freq.get, reverse=True) | |
| return keywords[:max_keywords] | |
| def extract_tokens(text): | |
| doc = nlp(text) | |
| tokens = [token.lemma_.lower().strip() for token in doc if not token.is_stop and token.is_ascii] | |
| return tokens | |
| data['keywords'] = data['description'].apply(extract_keywords) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment