UNT Linguistics at SemEval-2020 Task 12: Linear SVC with Pre-trained Word Embeddings as Document Vectors and Targeted Linguistic Features.
Jared FromknechtAlexis PalmerPublished in: SemEval@COLING (2020)
Keyphrases
- linguistic features
- pre trained
- linguistic knowledge
- word sense disambiguation
- sentence level
- part of speech
- natural language processing
- translation model
- vector space
- word sense
- wordnet
- named entities
- structural features
- natural language
- semantic features
- noun phrases
- training data
- text documents
- document collections
- co occurrence
- keywords
- feature set
- text classification
- sentiment analysis
- document clustering
- named entity recognition
- information retrieval systems
- n gram
- news stories
- tf idf
- low dimensional
- multi document summarization
- cross lingual
- text categorization
- information retrieval
- cross language information retrieval
- text summarization
- language model
- vector space model
- dimensionality reduction
- information extraction
- semantic similarity