FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3201769072> ?p ?o ?g. }

• W3201769072 abstract "We study multilingual AMR parsing from the perspective of knowledge distillation, where the aim is to learn and improve a multilingual AMR parser by using an existing English parser as its teacher. We constrain our exploration in a strict multilingual setting: there is but one model to parse all different languages including English. We identify that noisy input and precise output are the key to successful distillation. Together with extensive pre-training, we obtain an AMR parser whose performances surpass all previously published results on four different foreign languages, including German, Spanish, Italian, and Chinese, by large margins (up to 18.8 textsc{Smatch} points on Chinese and on average 11.3 textsc{Smatch} points). Our parser also achieves comparable performance on English to the latest state-of-the-art English-only parser." @default.
• W3201769072 created "2021-10-11" @default.
• W3201769072 creator A5016147639 @default.
• W3201769072 creator A5018582154 @default.
• W3201769072 creator A5022526821 @default.
• W3201769072 creator A5061528283 @default.
• W3201769072 creator A5086674741 @default.
• W3201769072 date "2021-01-01" @default.
• W3201769072 modified "2023-10-18" @default.
• W3201769072 title "Multilingual AMR Parsing with Noisy Knowledge Distillation" @default.
• W3201769072 cites W1821462560 @default.
• W3201769072 cites W2134797427 @default.
• W3201769072 cites W2149837184 @default.
• W3201769072 cites W22168010 @default.
• W3201769072 cites W2250375035 @default.
• W3201769072 cites W2250999268 @default.
• W3201769072 cites W2251071803 @default.
• W3201769072 cites W2252123671 @default.
• W3201769072 cites W2252151594 @default.
• W3201769072 cites W2294370754 @default.
• W3201769072 cites W2561238782 @default.
• W3201769072 cites W2587694128 @default.
• W3201769072 cites W2606900862 @default.
• W3201769072 cites W2619249607 @default.
• W3201769072 cites W2739879705 @default.
• W3201769072 cites W2767206889 @default.
• W3201769072 cites W2807626952 @default.
• W3201769072 cites W2890996951 @default.
• W3201769072 cites W2952650870 @default.
• W3201769072 cites W2962906084 @default.
• W3201769072 cites W2963213121 @default.
• W3201769072 cites W2963341956 @default.
• W3201769072 cites W2963350559 @default.
• W3201769072 cites W2963403868 @default.
• W3201769072 cites W2963537354 @default.
• W3201769072 cites W2964116568 @default.
• W3201769072 cites W2964118293 @default.
• W3201769072 cites W2964253663 @default.
• W3201769072 cites W2966469393 @default.
• W3201769072 cites W2970796523 @default.
• W3201769072 cites W2970917831 @default.
• W3201769072 cites W2972961728 @default.
• W3201769072 cites W2978017171 @default.
• W3201769072 cites W2982399380 @default.
• W3201769072 cites W2986772082 @default.
• W3201769072 cites W2994689640 @default.
• W3201769072 cites W3014635508 @default.
• W3201769072 cites W3035390927 @default.
• W3201769072 cites W3046368065 @default.
• W3201769072 cites W3082928416 @default.
• W3201769072 cites W3087395956 @default.
• W3201769072 cites W3098824823 @default.
• W3201769072 cites W3099405210 @default.
• W3201769072 cites W3101221466 @default.
• W3201769072 cites W3102483398 @default.
• W3201769072 cites W3104890489 @default.
• W3201769072 cites W3107803811 @default.
• W3201769072 cites W3107826490 @default.
• W3201769072 cites W3128056179 @default.
• W3201769072 cites W3168065076 @default.
• W3201769072 cites W3173677700 @default.
• W3201769072 cites W3176355530 @default.
• W3201769072 doi "https://doi.org/10.18653/v1/2021.findings-emnlp.237" @default.
• W3201769072 hasPublicationYear "2021" @default.
• W3201769072 type Work @default.
• W3201769072 sameAs 3201769072 @default.
• W3201769072 citedByCount "1" @default.
• W3201769072 countsByYear W32017690722023 @default.
• W3201769072 crossrefType "proceedings-article" @default.
• W3201769072 hasAuthorship W3201769072A5016147639 @default.
• W3201769072 hasAuthorship W3201769072A5018582154 @default.
• W3201769072 hasAuthorship W3201769072A5022526821 @default.
• W3201769072 hasAuthorship W3201769072A5061528283 @default.
• W3201769072 hasAuthorship W3201769072A5086674741 @default.
• W3201769072 hasBestOaLocation W32017690721 @default.
• W3201769072 hasConcept C138885662 @default.
• W3201769072 hasConcept C154775046 @default.
• W3201769072 hasConcept C154945302 @default.
• W3201769072 hasConcept C178790620 @default.
• W3201769072 hasConcept C185592680 @default.
• W3201769072 hasConcept C186644900 @default.
• W3201769072 hasConcept C204030448 @default.
• W3201769072 hasConcept C204321447 @default.
• W3201769072 hasConcept C26517878 @default.
• W3201769072 hasConcept C38652104 @default.
• W3201769072 hasConcept C41008148 @default.
• W3201769072 hasConcept C41895202 @default.
• W3201769072 hasConceptScore W3201769072C138885662 @default.
• W3201769072 hasConceptScore W3201769072C154775046 @default.
• W3201769072 hasConceptScore W3201769072C154945302 @default.
• W3201769072 hasConceptScore W3201769072C178790620 @default.
• W3201769072 hasConceptScore W3201769072C185592680 @default.
• W3201769072 hasConceptScore W3201769072C186644900 @default.
• W3201769072 hasConceptScore W3201769072C204030448 @default.
• W3201769072 hasConceptScore W3201769072C204321447 @default.
• W3201769072 hasConceptScore W3201769072C26517878 @default.
• W3201769072 hasConceptScore W3201769072C38652104 @default.
• W3201769072 hasConceptScore W3201769072C41008148 @default.
• W3201769072 hasConceptScore W3201769072C41895202 @default.
• W3201769072 hasLocation W32017690721 @default.

• next