Matches in SemOpenAlex for { <https://semopenalex.org/work/W2808482853> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W2808482853 abstract "Most existing Chinese word segmentation (CWS) methods are usually supervised. Hence, large-scale annotated domain-specific datasets are needed for training. In this paper, we seek to address the problem of CWS for the resource-poor domains that lack annotated data. A novel neural network model is proposed to incorporate unlabeled and partially-labeled data. To make use of unlabeled data, we combine a bidirectional LSTM segmentation model with two character-level language models using a gate mechanism. These language models can capture co-occurrence information. To make use of partially-labeled data, we modify the original cross entropy loss function of RNN. Experimental results demonstrate that the method performs well on CWS tasks in a series of domains." @default.
- W2808482853 created "2018-06-21" @default.
- W2808482853 creator A5026984704 @default.
- W2808482853 creator A5063819430 @default.
- W2808482853 creator A5074195514 @default.
- W2808482853 creator A5086418698 @default.
- W2808482853 date "2018-07-01" @default.
- W2808482853 modified "2023-09-27" @default.
- W2808482853 title "Neural Networks Incorporating Unlabeled and Partially-labeled Data for Cross-domain Chinese Word Segmentation" @default.
- W2808482853 cites W2010576059 @default.
- W2808482853 cites W2114930007 @default.
- W2808482853 cites W2126504272 @default.
- W2808482853 cites W2137281231 @default.
- W2808482853 cites W2149710647 @default.
- W2808482853 cites W2163377725 @default.
- W2808482853 cites W2250542158 @default.
- W2808482853 cites W2251797597 @default.
- W2808482853 cites W2341695656 @default.
- W2808482853 cites W2404744763 @default.
- W2808482853 cites W2516334389 @default.
- W2808482853 cites W2774687429 @default.
- W2808482853 cites W2963563735 @default.
- W2808482853 cites W2963628345 @default.
- W2808482853 cites W2963706742 @default.
- W2808482853 doi "https://doi.org/10.24963/ijcai.2018/640" @default.
- W2808482853 hasPublicationYear "2018" @default.
- W2808482853 type Work @default.
- W2808482853 sameAs 2808482853 @default.
- W2808482853 citedByCount "14" @default.
- W2808482853 countsByYear W28084828532019 @default.
- W2808482853 countsByYear W28084828532020 @default.
- W2808482853 countsByYear W28084828532021 @default.
- W2808482853 countsByYear W28084828532022 @default.
- W2808482853 crossrefType "proceedings-article" @default.
- W2808482853 hasAuthorship W2808482853A5026984704 @default.
- W2808482853 hasAuthorship W2808482853A5063819430 @default.
- W2808482853 hasAuthorship W2808482853A5074195514 @default.
- W2808482853 hasAuthorship W2808482853A5086418698 @default.
- W2808482853 hasBestOaLocation W28084828531 @default.
- W2808482853 hasConcept C106301342 @default.
- W2808482853 hasConcept C119857082 @default.
- W2808482853 hasConcept C121332964 @default.
- W2808482853 hasConcept C134306372 @default.
- W2808482853 hasConcept C137293760 @default.
- W2808482853 hasConcept C138885662 @default.
- W2808482853 hasConcept C153180895 @default.
- W2808482853 hasConcept C154945302 @default.
- W2808482853 hasConcept C167981619 @default.
- W2808482853 hasConcept C204321447 @default.
- W2808482853 hasConcept C2524010 @default.
- W2808482853 hasConcept C2776145971 @default.
- W2808482853 hasConcept C2780861071 @default.
- W2808482853 hasConcept C33923547 @default.
- W2808482853 hasConcept C36503486 @default.
- W2808482853 hasConcept C41008148 @default.
- W2808482853 hasConcept C41895202 @default.
- W2808482853 hasConcept C50644808 @default.
- W2808482853 hasConcept C62520636 @default.
- W2808482853 hasConcept C89600930 @default.
- W2808482853 hasConcept C90805587 @default.
- W2808482853 hasConcept C98501671 @default.
- W2808482853 hasConceptScore W2808482853C106301342 @default.
- W2808482853 hasConceptScore W2808482853C119857082 @default.
- W2808482853 hasConceptScore W2808482853C121332964 @default.
- W2808482853 hasConceptScore W2808482853C134306372 @default.
- W2808482853 hasConceptScore W2808482853C137293760 @default.
- W2808482853 hasConceptScore W2808482853C138885662 @default.
- W2808482853 hasConceptScore W2808482853C153180895 @default.
- W2808482853 hasConceptScore W2808482853C154945302 @default.
- W2808482853 hasConceptScore W2808482853C167981619 @default.
- W2808482853 hasConceptScore W2808482853C204321447 @default.
- W2808482853 hasConceptScore W2808482853C2524010 @default.
- W2808482853 hasConceptScore W2808482853C2776145971 @default.
- W2808482853 hasConceptScore W2808482853C2780861071 @default.
- W2808482853 hasConceptScore W2808482853C33923547 @default.
- W2808482853 hasConceptScore W2808482853C36503486 @default.
- W2808482853 hasConceptScore W2808482853C41008148 @default.
- W2808482853 hasConceptScore W2808482853C41895202 @default.
- W2808482853 hasConceptScore W2808482853C50644808 @default.
- W2808482853 hasConceptScore W2808482853C62520636 @default.
- W2808482853 hasConceptScore W2808482853C89600930 @default.
- W2808482853 hasConceptScore W2808482853C90805587 @default.
- W2808482853 hasConceptScore W2808482853C98501671 @default.
- W2808482853 hasLocation W28084828531 @default.
- W2808482853 hasOpenAccess W2808482853 @default.
- W2808482853 hasPrimaryLocation W28084828531 @default.
- W2808482853 hasRelatedWork W1978843799 @default.
- W2808482853 hasRelatedWork W2114478103 @default.
- W2808482853 hasRelatedWork W2420187884 @default.
- W2808482853 hasRelatedWork W2555559948 @default.
- W2808482853 hasRelatedWork W2804033347 @default.
- W2808482853 hasRelatedWork W2806021948 @default.
- W2808482853 hasRelatedWork W2951061418 @default.
- W2808482853 hasRelatedWork W2954089321 @default.
- W2808482853 hasRelatedWork W4350982 @default.
- W2808482853 hasRelatedWork W4353007076 @default.
- W2808482853 isParatext "false" @default.
- W2808482853 isRetracted "false" @default.
- W2808482853 magId "2808482853" @default.
- W2808482853 workType "article" @default.