Matches in SemOpenAlex for { <https://semopenalex.org/work/W3211424777> ?p ?o ?g. }
- W3211424777 abstract "Thanks to the strong representation learning capability of deep learning, especially pre-training techniques with language model loss, dependency parsing has achieved great performance boost in the in-domain scenario with abundant labeled training data for target domains. However, the parsing community has to face the more realistic setting where the parsing performance drops drastically when labeled data only exists for several fixed out-domains. In this work, we propose a novel model for multi-source cross-domain dependency parsing. The model consists of two components, i.e., a parameter generation network for distinguishing domain-specific features, and an adversarial network for learning domain-invariant representations. Experiments on a recently released NLPCC-2019 dataset for multi-domain dependency parsing show that our model can consistently improve cross-domain parsing performance by about 2 points in averaged labeled attachment accuracy (LAS) over strong BERT-enhanced baselines. Detailed analysis is conducted to gain more insights on contributions of the two components." @default.
- W3211424777 created "2021-11-22" @default.
- W3211424777 creator A5004953265 @default.
- W3211424777 creator A5020858666 @default.
- W3211424777 creator A5023672919 @default.
- W3211424777 creator A5053204257 @default.
- W3211424777 creator A5053345000 @default.
- W3211424777 creator A5060002817 @default.
- W3211424777 creator A5065838678 @default.
- W3211424777 date "2021-01-01" @default.
- W3211424777 modified "2023-09-27" @default.
- W3211424777 title "APGN: Adversarial and Parameter Generation Networks for Multi-Source Cross-Domain Dependency Parsing" @default.
- W3211424777 cites W1567570606 @default.
- W3211424777 cites W2002586403 @default.
- W3211424777 cites W2120354757 @default.
- W3211424777 cites W2128634885 @default.
- W3211424777 cites W2137806537 @default.
- W3211424777 cites W2142222368 @default.
- W3211424777 cites W2145837098 @default.
- W3211424777 cites W2153579005 @default.
- W3211424777 cites W2250861254 @default.
- W3211424777 cites W2301095666 @default.
- W3211424777 cites W2312004824 @default.
- W3211424777 cites W2396230549 @default.
- W3211424777 cites W2540485556 @default.
- W3211424777 cites W2741239878 @default.
- W3211424777 cites W2756978580 @default.
- W3211424777 cites W2758609995 @default.
- W3211424777 cites W2888456631 @default.
- W3211424777 cites W2891602716 @default.
- W3211424777 cites W2891691791 @default.
- W3211424777 cites W2892244498 @default.
- W3211424777 cites W2950739345 @default.
- W3211424777 cites W2963571341 @default.
- W3211424777 cites W2963826681 @default.
- W3211424777 cites W2966423804 @default.
- W3211424777 cites W2976939606 @default.
- W3211424777 cites W2977052846 @default.
- W3211424777 cites W2977149219 @default.
- W3211424777 cites W2997197207 @default.
- W3211424777 cites W2997617245 @default.
- W3211424777 cites W2998103904 @default.
- W3211424777 cites W3034665873 @default.
- W3211424777 cites W3095012670 @default.
- W3211424777 cites W3104783994 @default.
- W3211424777 doi "https://doi.org/10.18653/v1/2021.findings-emnlp.149" @default.
- W3211424777 hasPublicationYear "2021" @default.
- W3211424777 type Work @default.
- W3211424777 sameAs 3211424777 @default.
- W3211424777 citedByCount "0" @default.
- W3211424777 crossrefType "proceedings-article" @default.
- W3211424777 hasAuthorship W3211424777A5004953265 @default.
- W3211424777 hasAuthorship W3211424777A5020858666 @default.
- W3211424777 hasAuthorship W3211424777A5023672919 @default.
- W3211424777 hasAuthorship W3211424777A5053204257 @default.
- W3211424777 hasAuthorship W3211424777A5053345000 @default.
- W3211424777 hasAuthorship W3211424777A5060002817 @default.
- W3211424777 hasAuthorship W3211424777A5065838678 @default.
- W3211424777 hasBestOaLocation W32114247771 @default.
- W3211424777 hasConcept C119857082 @default.
- W3211424777 hasConcept C134306372 @default.
- W3211424777 hasConcept C154945302 @default.
- W3211424777 hasConcept C164883195 @default.
- W3211424777 hasConcept C17744445 @default.
- W3211424777 hasConcept C186644900 @default.
- W3211424777 hasConcept C19768560 @default.
- W3211424777 hasConcept C199539241 @default.
- W3211424777 hasConcept C204321447 @default.
- W3211424777 hasConcept C2776359362 @default.
- W3211424777 hasConcept C33923547 @default.
- W3211424777 hasConcept C36503486 @default.
- W3211424777 hasConcept C37736160 @default.
- W3211424777 hasConcept C41008148 @default.
- W3211424777 hasConcept C42560504 @default.
- W3211424777 hasConcept C60690694 @default.
- W3211424777 hasConcept C94625758 @default.
- W3211424777 hasConceptScore W3211424777C119857082 @default.
- W3211424777 hasConceptScore W3211424777C134306372 @default.
- W3211424777 hasConceptScore W3211424777C154945302 @default.
- W3211424777 hasConceptScore W3211424777C164883195 @default.
- W3211424777 hasConceptScore W3211424777C17744445 @default.
- W3211424777 hasConceptScore W3211424777C186644900 @default.
- W3211424777 hasConceptScore W3211424777C19768560 @default.
- W3211424777 hasConceptScore W3211424777C199539241 @default.
- W3211424777 hasConceptScore W3211424777C204321447 @default.
- W3211424777 hasConceptScore W3211424777C2776359362 @default.
- W3211424777 hasConceptScore W3211424777C33923547 @default.
- W3211424777 hasConceptScore W3211424777C36503486 @default.
- W3211424777 hasConceptScore W3211424777C37736160 @default.
- W3211424777 hasConceptScore W3211424777C41008148 @default.
- W3211424777 hasConceptScore W3211424777C42560504 @default.
- W3211424777 hasConceptScore W3211424777C60690694 @default.
- W3211424777 hasConceptScore W3211424777C94625758 @default.
- W3211424777 hasLocation W32114247771 @default.
- W3211424777 hasOpenAccess W3211424777 @default.
- W3211424777 hasPrimaryLocation W32114247771 @default.
- W3211424777 hasRelatedWork W1568793342 @default.
- W3211424777 hasRelatedWork W2058621701 @default.
- W3211424777 hasRelatedWork W2200456380 @default.
- W3211424777 hasRelatedWork W2250574586 @default.