UDPipe: Trainable Pipeline for Processing CoNLL-U Files Performing Tokenization, Morphological Analysis, POS Tagging and Parsing.
Milan StrakaJan HajicJana StrakováPublished in: LREC (2016)
Keyphrases
- pos tagging
- morphological analysis
- dependency parsing
- named entity recognition
- named entities
- part of speech
- penn treebank
- chinese word segmentation
- semantic role labeling
- word segmentation
- domain adaptation
- machine translation
- natural language processing
- information extraction
- n gram
- pos taggers
- conditional random fields
- parse tree
- text documents
- maximum entropy
- unsupervised learning
- image classification
- information retrieval systems