Matches in SemOpenAlex for { <https://semopenalex.org/work/W3213037944> ?p ?o ?g. }
- W3213037944 endingPage "9473" @default.
- W3213037944 startingPage "9457" @default.
- W3213037944 abstract "We compare two orthogonal semi-supervised learning techniques, namely tri-training and pretrained word embeddings, in the task of dependency parsing. We explore language-specific FastText and ELMo embeddings and multilingual BERT embeddings. We focus on a low resource scenario as semi-supervised learning can be expected to have the most impact here. Based on treebank size and available ELMo models, we select Hungarian, Uyghur (a zero-shot language for mBERT) and Vietnamese. Furthermore, we include English in a simulated low-resource setting. We find that pretrained word embeddings make more effective use of unlabelled data than tri-training but that the two approaches can be successfully combined." @default.
- W3213037944 created "2021-11-22" @default.
- W3213037944 creator A5026305513 @default.
- W3213037944 creator A5066497689 @default.
- W3213037944 date "2021-11-01" @default.
- W3213037944 modified "2023-09-23" @default.
- W3213037944 title "Revisiting Tri-training of Dependency Parsers" @default.
- W3213037944 cites W121244246 @default.
- W3213037944 cites W1536764988 @default.
- W3213037944 cites W1567570606 @default.
- W3213037944 cites W1745817670 @default.
- W3213037944 cites W2002371623 @default.
- W3213037944 cites W2002586403 @default.
- W3213037944 cites W2079359777 @default.
- W3213037944 cites W2117921985 @default.
- W3213037944 cites W2133556223 @default.
- W3213037944 cites W2138382875 @default.
- W3213037944 cites W2140398982 @default.
- W3213037944 cites W2161222299 @default.
- W3213037944 cites W2163568299 @default.
- W3213037944 cites W2250263931 @default.
- W3213037944 cites W2283415767 @default.
- W3213037944 cites W2405246503 @default.
- W3213037944 cites W2493916176 @default.
- W3213037944 cites W2673116624 @default.
- W3213037944 cites W2740840489 @default.
- W3213037944 cites W2786459410 @default.
- W3213037944 cites W2808139377 @default.
- W3213037944 cites W2891602716 @default.
- W3213037944 cites W2898879711 @default.
- W3213037944 cites W2911959277 @default.
- W3213037944 cites W2949917295 @default.
- W3213037944 cites W2962739339 @default.
- W3213037944 cites W2963069010 @default.
- W3213037944 cites W2963326042 @default.
- W3213037944 cites W2963341956 @default.
- W3213037944 cites W2969873034 @default.
- W3213037944 cites W2998635301 @default.
- W3213037944 cites W3037789307 @default.
- W3213037944 cites W3102021588 @default.
- W3213037944 cites W3118485687 @default.
- W3213037944 hasPublicationYear "2021" @default.
- W3213037944 type Work @default.
- W3213037944 sameAs 3213037944 @default.
- W3213037944 citedByCount "0" @default.
- W3213037944 crossrefType "proceedings-article" @default.
- W3213037944 hasAuthorship W3213037944A5026305513 @default.
- W3213037944 hasAuthorship W3213037944A5066497689 @default.
- W3213037944 hasConcept C103621254 @default.
- W3213037944 hasConcept C120665830 @default.
- W3213037944 hasConcept C121332964 @default.
- W3213037944 hasConcept C138885662 @default.
- W3213037944 hasConcept C154945302 @default.
- W3213037944 hasConcept C162324750 @default.
- W3213037944 hasConcept C164883195 @default.
- W3213037944 hasConcept C186644900 @default.
- W3213037944 hasConcept C187736073 @default.
- W3213037944 hasConcept C192209626 @default.
- W3213037944 hasConcept C19768560 @default.
- W3213037944 hasConcept C204321447 @default.
- W3213037944 hasConcept C206134035 @default.
- W3213037944 hasConcept C2780451532 @default.
- W3213037944 hasConcept C41008148 @default.
- W3213037944 hasConcept C41895202 @default.
- W3213037944 hasConcept C51632099 @default.
- W3213037944 hasConcept C90805587 @default.
- W3213037944 hasConceptScore W3213037944C103621254 @default.
- W3213037944 hasConceptScore W3213037944C120665830 @default.
- W3213037944 hasConceptScore W3213037944C121332964 @default.
- W3213037944 hasConceptScore W3213037944C138885662 @default.
- W3213037944 hasConceptScore W3213037944C154945302 @default.
- W3213037944 hasConceptScore W3213037944C162324750 @default.
- W3213037944 hasConceptScore W3213037944C164883195 @default.
- W3213037944 hasConceptScore W3213037944C186644900 @default.
- W3213037944 hasConceptScore W3213037944C187736073 @default.
- W3213037944 hasConceptScore W3213037944C192209626 @default.
- W3213037944 hasConceptScore W3213037944C19768560 @default.
- W3213037944 hasConceptScore W3213037944C204321447 @default.
- W3213037944 hasConceptScore W3213037944C206134035 @default.
- W3213037944 hasConceptScore W3213037944C2780451532 @default.
- W3213037944 hasConceptScore W3213037944C41008148 @default.
- W3213037944 hasConceptScore W3213037944C41895202 @default.
- W3213037944 hasConceptScore W3213037944C51632099 @default.
- W3213037944 hasConceptScore W3213037944C90805587 @default.
- W3213037944 hasLocation W32130379441 @default.
- W3213037944 hasOpenAccess W3213037944 @default.
- W3213037944 hasPrimaryLocation W32130379441 @default.
- W3213037944 hasRelatedWork W1591341683 @default.
- W3213037944 hasRelatedWork W2158139315 @default.
- W3213037944 hasRelatedWork W2187430830 @default.
- W3213037944 hasRelatedWork W2575172791 @default.
- W3213037944 hasRelatedWork W2922170191 @default.
- W3213037944 hasRelatedWork W2941819978 @default.
- W3213037944 hasRelatedWork W2947018532 @default.
- W3213037944 hasRelatedWork W2949604985 @default.
- W3213037944 hasRelatedWork W2963563735 @default.
- W3213037944 hasRelatedWork W2969873034 @default.
- W3213037944 hasRelatedWork W2998188449 @default.