Matches in SemOpenAlex for { <https://semopenalex.org/work/W2963393721> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W2963393721 abstract "Latent tree learning models learn to parse a sentence without syntactic supervision, and use that parse to build the sentence representation. Existing work on such models has shown that, while they perform well on tasks like sentence classification, they do not learn grammars that conform to any plausible semantic or syntactic formalism (Williams et al., 2018a). Studying the parsing ability of such models in natural language can be challenging due to the inherent complexities of natural language, like having several valid parses for a single sentence. In this paper we introduce ListOps, a toy dataset created to study the parsing ability of latent tree models. ListOps sequences are in the style of prefix arithmetic. The dataset is designed to have a single correct parsing strategy that a system needs to learn to succeed at the task. We show that the current leading latent tree models are unable to learn to parse and succeed at ListOps. These models achieve accuracies worse than purely sequential RNNs." @default.
- W2963393721 created "2019-07-30" @default.
- W2963393721 creator A5013626682 @default.
- W2963393721 creator A5067390670 @default.
- W2963393721 date "2018-01-01" @default.
- W2963393721 modified "2023-10-11" @default.
- W2963393721 title "ListOps: A Diagnostic Dataset for Latent Tree Learning" @default.
- W2963393721 cites W1502293651 @default.
- W2963393721 cites W1525961042 @default.
- W2963393721 cites W1793121960 @default.
- W2963393721 cites W1840435438 @default.
- W2963393721 cites W1970961429 @default.
- W2963393721 cites W2064675550 @default.
- W2963393721 cites W2133585753 @default.
- W2963393721 cites W2152907450 @default.
- W2963393721 cites W2547875792 @default.
- W2963393721 cites W2619818172 @default.
- W2963393721 cites W2963355447 @default.
- W2963393721 cites W2963451457 @default.
- W2963393721 cites W2963580443 @default.
- W2963393721 cites W2963846996 @default.
- W2963393721 cites W2964091467 @default.
- W2963393721 cites W2964121744 @default.
- W2963393721 cites W71795751 @default.
- W2963393721 doi "https://doi.org/10.18653/v1/n18-4013" @default.
- W2963393721 hasPublicationYear "2018" @default.
- W2963393721 type Work @default.
- W2963393721 sameAs 2963393721 @default.
- W2963393721 citedByCount "48" @default.
- W2963393721 countsByYear W29633937212018 @default.
- W2963393721 countsByYear W29633937212019 @default.
- W2963393721 countsByYear W29633937212020 @default.
- W2963393721 countsByYear W29633937212021 @default.
- W2963393721 countsByYear W29633937212022 @default.
- W2963393721 countsByYear W29633937212023 @default.
- W2963393721 crossrefType "proceedings-article" @default.
- W2963393721 hasAuthorship W2963393721A5013626682 @default.
- W2963393721 hasAuthorship W2963393721A5067390670 @default.
- W2963393721 hasBestOaLocation W29633937211 @default.
- W2963393721 hasConcept C113174947 @default.
- W2963393721 hasConcept C134306372 @default.
- W2963393721 hasConcept C137293760 @default.
- W2963393721 hasConcept C154945302 @default.
- W2963393721 hasConcept C162319229 @default.
- W2963393721 hasConcept C163797641 @default.
- W2963393721 hasConcept C186644900 @default.
- W2963393721 hasConcept C195324797 @default.
- W2963393721 hasConcept C199360897 @default.
- W2963393721 hasConcept C204321447 @default.
- W2963393721 hasConcept C2777530160 @default.
- W2963393721 hasConcept C2781466058 @default.
- W2963393721 hasConcept C33923547 @default.
- W2963393721 hasConcept C41008148 @default.
- W2963393721 hasConcept C53893814 @default.
- W2963393721 hasConceptScore W2963393721C113174947 @default.
- W2963393721 hasConceptScore W2963393721C134306372 @default.
- W2963393721 hasConceptScore W2963393721C137293760 @default.
- W2963393721 hasConceptScore W2963393721C154945302 @default.
- W2963393721 hasConceptScore W2963393721C162319229 @default.
- W2963393721 hasConceptScore W2963393721C163797641 @default.
- W2963393721 hasConceptScore W2963393721C186644900 @default.
- W2963393721 hasConceptScore W2963393721C195324797 @default.
- W2963393721 hasConceptScore W2963393721C199360897 @default.
- W2963393721 hasConceptScore W2963393721C204321447 @default.
- W2963393721 hasConceptScore W2963393721C2777530160 @default.
- W2963393721 hasConceptScore W2963393721C2781466058 @default.
- W2963393721 hasConceptScore W2963393721C33923547 @default.
- W2963393721 hasConceptScore W2963393721C41008148 @default.
- W2963393721 hasConceptScore W2963393721C53893814 @default.
- W2963393721 hasLocation W29633937211 @default.
- W2963393721 hasLocation W29633937212 @default.
- W2963393721 hasOpenAccess W2963393721 @default.
- W2963393721 hasPrimaryLocation W29633937211 @default.
- W2963393721 hasRelatedWork W159132833 @default.
- W2963393721 hasRelatedWork W1860968280 @default.
- W2963393721 hasRelatedWork W1976402971 @default.
- W2963393721 hasRelatedWork W2074944565 @default.
- W2963393721 hasRelatedWork W2167662847 @default.
- W2963393721 hasRelatedWork W2796705611 @default.
- W2963393721 hasRelatedWork W3155267019 @default.
- W2963393721 hasRelatedWork W3200292358 @default.
- W2963393721 hasRelatedWork W4287231412 @default.
- W2963393721 hasRelatedWork W4302359736 @default.
- W2963393721 isParatext "false" @default.
- W2963393721 isRetracted "false" @default.
- W2963393721 magId "2963393721" @default.
- W2963393721 workType "article" @default.