Samsung Poland NLP Team at SemEval-2016 Task 1: Necessity for diversity; combining recursive autoencoders, WordNet and ensemble methods to measure semantic similarity.
Barbara RychalskaKatarzyna PakulskaKrystyna ChodorowskaWojciech WalczakPiotr AndruszkiewiczPublished in: SemEval@NAACL-HLT (2016)
Keyphrases
- wordnet
- semantic similarity
- ensemble methods
- word sense disambiguation
- natural language processing
- semantic similarity measure
- sense disambiguation
- co occurrence
- semantic information
- semantic relatedness
- benchmark datasets
- prediction accuracy
- machine learning methods
- semantic relationships
- decision trees
- semantic relations
- lexical resources
- similarity measure
- vector space model
- semantic distance
- semantically similar
- text documents
- semantic features
- lexical knowledge
- lexical database
- word sense
- word pairs
- linguistic knowledge
- knowledge base
- named entity recognition
- information extraction
- part of speech
- keywords
- cosine similarity
- word similarity
- machine learning
- semantic similarity between words
- document similarity
- semantic representations
- low level
- high level
- web pages
- artificial intelligence