FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2994806031> ?p ?o ?g. }

• W2994806031 endingPage "713" @default.
• W2994806031 startingPage "695" @default.
• W2994806031 abstract "Neural dependency parsing has proven very effective, achieving state-of-the-art results on numerous domains and languages. Unfortunately, it requires large amounts of labeled data, which is costly and laborious to create. In this paper we propose a self-training algorithm that alleviates this annotation bottleneck by training a parser on its own output. Our Deep Contextualized Self-training (DCST) algorithm utilizes representation models trained on sequence labeling tasks that are derived from the parser’s output when applied to unlabeled data, and integrates these models with the base parser through a gating mechanism. We conduct experiments across multiple languages, both in low resource in-domain and in cross-domain setups, and demonstrate that DCST substantially outperforms traditional self-training as well as recent semi-supervised training methods. 1" @default.
• W2994806031 created "2019-12-26" @default.
• W2994806031 creator A5044349276 @default.
• W2994806031 creator A5054952724 @default.
• W2994806031 date "2019-11-01" @default.
• W2994806031 modified "2023-10-13" @default.
• W2994806031 title "Deep Contextualized Self-training for Low Resource Dependency Parsing" @default.
• W2994806031 cites W2030866871 @default.
• W2994806031 cites W2048679005 @default.
• W2994806031 cites W2133556223 @default.
• W2994806031 cites W2152005244 @default.
• W2994806031 cites W2250539671 @default.
• W2994806031 cites W2251771443 @default.
• W2994806031 cites W2301095666 @default.
• W2994806031 cites W2460319482 @default.
• W2994806031 cites W2604593109 @default.
• W2994806031 cites W2740345664 @default.
• W2994806031 cites W2798935874 @default.
• W2994806031 cites W2883872108 @default.
• W2994806031 cites W2891602716 @default.
• W2994806031 cites W2914924671 @default.
• W2994806031 cites W2962909510 @default.
• W2994806031 cites W2962982474 @default.
• W2994806031 cites W2964266061 @default.
• W2994806031 cites W4246185962 @default.
• W2994806031 doi "https://doi.org/10.1162/tacl_a_00294" @default.
• W2994806031 hasPublicationYear "2019" @default.
• W2994806031 type Work @default.
• W2994806031 sameAs 2994806031 @default.
• W2994806031 citedByCount "23" @default.
• W2994806031 countsByYear W29948060312020 @default.
• W2994806031 countsByYear W29948060312021 @default.
• W2994806031 countsByYear W29948060312022 @default.
• W2994806031 countsByYear W29948060312023 @default.
• W2994806031 crossrefType "journal-article" @default.
• W2994806031 hasAuthorship W2994806031A5044349276 @default.
• W2994806031 hasAuthorship W2994806031A5054952724 @default.
• W2994806031 hasBestOaLocation W29948060311 @default.
• W2994806031 hasConcept C119857082 @default.
• W2994806031 hasConcept C134306372 @default.
• W2994806031 hasConcept C149635348 @default.
• W2994806031 hasConcept C154945302 @default.
• W2994806031 hasConcept C162324750 @default.
• W2994806031 hasConcept C164883195 @default.
• W2994806031 hasConcept C17744445 @default.
• W2994806031 hasConcept C186644900 @default.
• W2994806031 hasConcept C187736073 @default.
• W2994806031 hasConcept C19768560 @default.
• W2994806031 hasConcept C199539241 @default.
• W2994806031 hasConcept C204321447 @default.
• W2994806031 hasConcept C2776321320 @default.
• W2994806031 hasConcept C2776359362 @default.
• W2994806031 hasConcept C2780451532 @default.
• W2994806031 hasConcept C2780513914 @default.
• W2994806031 hasConcept C33923547 @default.
• W2994806031 hasConcept C35639132 @default.
• W2994806031 hasConcept C36503486 @default.
• W2994806031 hasConcept C41008148 @default.
• W2994806031 hasConcept C51632099 @default.
• W2994806031 hasConcept C94625758 @default.
• W2994806031 hasConceptScore W2994806031C119857082 @default.
• W2994806031 hasConceptScore W2994806031C134306372 @default.
• W2994806031 hasConceptScore W2994806031C149635348 @default.
• W2994806031 hasConceptScore W2994806031C154945302 @default.
• W2994806031 hasConceptScore W2994806031C162324750 @default.
• W2994806031 hasConceptScore W2994806031C164883195 @default.
• W2994806031 hasConceptScore W2994806031C17744445 @default.
• W2994806031 hasConceptScore W2994806031C186644900 @default.
• W2994806031 hasConceptScore W2994806031C187736073 @default.
• W2994806031 hasConceptScore W2994806031C19768560 @default.
• W2994806031 hasConceptScore W2994806031C199539241 @default.
• W2994806031 hasConceptScore W2994806031C204321447 @default.
• W2994806031 hasConceptScore W2994806031C2776321320 @default.
• W2994806031 hasConceptScore W2994806031C2776359362 @default.
• W2994806031 hasConceptScore W2994806031C2780451532 @default.
• W2994806031 hasConceptScore W2994806031C2780513914 @default.
• W2994806031 hasConceptScore W2994806031C33923547 @default.
• W2994806031 hasConceptScore W2994806031C35639132 @default.
• W2994806031 hasConceptScore W2994806031C36503486 @default.
• W2994806031 hasConceptScore W2994806031C41008148 @default.
• W2994806031 hasConceptScore W2994806031C51632099 @default.
• W2994806031 hasConceptScore W2994806031C94625758 @default.
• W2994806031 hasLocation W29948060311 @default.
• W2994806031 hasLocation W29948060312 @default.
• W2994806031 hasOpenAccess W2994806031 @default.
• W2994806031 hasPrimaryLocation W29948060311 @default.
• W2994806031 hasRelatedWork W2098784136 @default.
• W2994806031 hasRelatedWork W2179743027 @default.
• W2994806031 hasRelatedWork W2251084681 @default.
• W2994806031 hasRelatedWork W287510790 @default.
• W2994806031 hasRelatedWork W2952664794 @default.
• W2994806031 hasRelatedWork W2953770453 @default.
• W2994806031 hasRelatedWork W2968543375 @default.
• W2994806031 hasRelatedWork W2987141700 @default.
• W2994806031 hasRelatedWork W4288558800 @default.
• W2994806031 hasRelatedWork W63925617 @default.
• W2994806031 hasVolume "7" @default.
• W2994806031 isParatext "false" @default.

• next