Matches in SemOpenAlex for { <https://semopenalex.org/work/W3175946245> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W3175946245 abstract "The combined use of neural scoring systems and BERT fine-tuning has led to very high results in many natural language processing (NLP) tasks. These high results raise two important questions about the contribution and the limitations of pretrained-language models: (i) what are the remaining errors in the bestperforming systems? (ii) what are the types of test examples where pretrained language models help the most? In this paper, we investigate both questions for the task of English discontinuous constituency parsing on the Penn Treebank, for which recent models obtain close to 95 F 1 score. To do so, we propose two methods for automatically analysing the errors of discontinuous parser. First, we annotate and release a test-suite focused on the syntactic phenomena responsible for discontinuities in the Penn Treebank, enabling us to obtain a per-phenomenon evaluation of a parser's output. Second, we extend the Berkeley Parser Analyser-a tool that classifies parsing errors according to predefined structural patterns-, to discontinuous trees. We apply both methods to characterize errors of a state-of-theart transition-based discontinuous parser, and to provide an overview of the contribution of BERT to this task." @default.
- W3175946245 created "2021-07-05" @default.
- W3175946245 creator A5006675504 @default.
- W3175946245 date "2021-01-01" @default.
- W3175946245 modified "2023-09-30" @default.
- W3175946245 title "BERT-Proof Syntactic Structures: Investigating Errors in Discontinuous Constituency Parsing" @default.
- W3175946245 cites W1632114991 @default.
- W3175946245 cites W168425931 @default.
- W3175946245 cites W190998322 @default.
- W3175946245 cites W1965364888 @default.
- W3175946245 cites W2015042937 @default.
- W3175946245 cites W2052847729 @default.
- W3175946245 cites W2121924470 @default.
- W3175946245 cites W2123311362 @default.
- W3175946245 cites W2132864397 @default.
- W3175946245 cites W2250369553 @default.
- W3175946245 cites W2250525101 @default.
- W3175946245 cites W2251719990 @default.
- W3175946245 cites W2336011916 @default.
- W3175946245 cites W2511889963 @default.
- W3175946245 cites W2515251660 @default.
- W3175946245 cites W2549835527 @default.
- W3175946245 cites W2563495010 @default.
- W3175946245 cites W2575705879 @default.
- W3175946245 cites W2735411217 @default.
- W3175946245 cites W2739852731 @default.
- W3175946245 cites W2759245546 @default.
- W3175946245 cites W2760532720 @default.
- W3175946245 cites W2798727047 @default.
- W3175946245 cites W2828651285 @default.
- W3175946245 cites W2888922637 @default.
- W3175946245 cites W2916601778 @default.
- W3175946245 cites W2918996109 @default.
- W3175946245 cites W2934008215 @default.
- W3175946245 cites W2962772361 @default.
- W3175946245 cites W2963084773 @default.
- W3175946245 cites W2963341956 @default.
- W3175946245 cites W2963403868 @default.
- W3175946245 cites W2963428826 @default.
- W3175946245 cites W2963643701 @default.
- W3175946245 cites W2963667932 @default.
- W3175946245 cites W2963751529 @default.
- W3175946245 cites W2970971581 @default.
- W3175946245 cites W2996824315 @default.
- W3175946245 cites W3037485215 @default.
- W3175946245 cites W3098824823 @default.
- W3175946245 cites W3104108644 @default.
- W3175946245 cites W3104536200 @default.
- W3175946245 cites W3168987555 @default.
- W3175946245 cites W3171639288 @default.
- W3175946245 doi "https://doi.org/10.18653/v1/2021.findings-acl.288" @default.
- W3175946245 hasPublicationYear "2021" @default.
- W3175946245 type Work @default.
- W3175946245 sameAs 3175946245 @default.
- W3175946245 citedByCount "2" @default.
- W3175946245 countsByYear W31759462452022 @default.
- W3175946245 countsByYear W31759462452023 @default.
- W3175946245 crossrefType "proceedings-article" @default.
- W3175946245 hasAuthorship W3175946245A5006675504 @default.
- W3175946245 hasBestOaLocation W31759462451 @default.
- W3175946245 hasConcept C154945302 @default.
- W3175946245 hasConcept C186644900 @default.
- W3175946245 hasConcept C199360897 @default.
- W3175946245 hasConcept C204321447 @default.
- W3175946245 hasConcept C28490314 @default.
- W3175946245 hasConcept C41008148 @default.
- W3175946245 hasConceptScore W3175946245C154945302 @default.
- W3175946245 hasConceptScore W3175946245C186644900 @default.
- W3175946245 hasConceptScore W3175946245C199360897 @default.
- W3175946245 hasConceptScore W3175946245C204321447 @default.
- W3175946245 hasConceptScore W3175946245C28490314 @default.
- W3175946245 hasConceptScore W3175946245C41008148 @default.
- W3175946245 hasLocation W31759462451 @default.
- W3175946245 hasLocation W31759462452 @default.
- W3175946245 hasLocation W31759462453 @default.
- W3175946245 hasLocation W31759462454 @default.
- W3175946245 hasLocation W31759462455 @default.
- W3175946245 hasOpenAccess W3175946245 @default.
- W3175946245 hasPrimaryLocation W31759462451 @default.
- W3175946245 hasRelatedWork W1512248002 @default.
- W3175946245 hasRelatedWork W1998962249 @default.
- W3175946245 hasRelatedWork W2026046761 @default.
- W3175946245 hasRelatedWork W2070147537 @default.
- W3175946245 hasRelatedWork W2167662847 @default.
- W3175946245 hasRelatedWork W2502722637 @default.
- W3175946245 hasRelatedWork W4235735989 @default.
- W3175946245 hasRelatedWork W1551406738 @default.
- W3175946245 hasRelatedWork W2467097043 @default.
- W3175946245 hasRelatedWork W2474495446 @default.
- W3175946245 isParatext "false" @default.
- W3175946245 isRetracted "false" @default.
- W3175946245 magId "3175946245" @default.
- W3175946245 workType "article" @default.