Matches in SemOpenAlex for { <https://semopenalex.org/work/W3213051760> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W3213051760 abstract "In computational linguistics, it has been shown that hierarchical structures make language models (LMs) more human-like. However, the previous literature has been agnostic about a parsing strategy of the hierarchical models. In this paper, we investigated whether hierarchical structures make LMs more human-like, and if so, which parsing strategy is most cognitively plausible. In order to address this question, we evaluated three LMs against human reading times in Japanese with head-final left-branching structures: Long Short-Term Memory (LSTM) as a sequential model and Recurrent Neural Network Grammars (RNNGs) with top-down and left-corner parsing strategies as hierarchical models. Our computational modeling demonstrated that left-corner RNNGs outperformed top-down RNNGs and LSTM, suggesting that hierarchical and left-corner architectures are more cognitively plausible than top-down or sequential architectures. In addition, the relationships between the cognitive plausibility and (i) perplexity, (ii) parsing, and (iii) beam size will also be discussed." @default.
- W3213051760 created "2021-11-22" @default.
- W3213051760 creator A5025796706 @default.
- W3213051760 creator A5076043621 @default.
- W3213051760 creator A5084221709 @default.
- W3213051760 date "2021-01-01" @default.
- W3213051760 modified "2023-09-23" @default.
- W3213051760 title "Modeling Human Sentence Processing with Left-Corner Recurrent Neural Network Grammars" @default.
- W3213051760 cites W1535183358 @default.
- W3213051760 cites W1574901103 @default.
- W3213051760 cites W1981379484 @default.
- W3213051760 cites W2014237504 @default.
- W3213051760 cites W2021916592 @default.
- W3213051760 cites W2033975289 @default.
- W3213051760 cites W2054125330 @default.
- W3213051760 cites W2102573550 @default.
- W3213051760 cites W2108010971 @default.
- W3213051760 cites W2118276816 @default.
- W3213051760 cites W2119728020 @default.
- W3213051760 cites W2157365695 @default.
- W3213051760 cites W2164418233 @default.
- W3213051760 cites W2554915555 @default.
- W3213051760 cites W2795342569 @default.
- W3213051760 cites W2798727047 @default.
- W3213051760 cites W2918996109 @default.
- W3213051760 cites W2962733492 @default.
- W3213051760 cites W2962784628 @default.
- W3213051760 cites W2963073938 @default.
- W3213051760 cites W2963250244 @default.
- W3213051760 cites W2963403868 @default.
- W3213051760 cites W2963751529 @default.
- W3213051760 cites W2964335542 @default.
- W3213051760 cites W3134106875 @default.
- W3213051760 cites W3175306105 @default.
- W3213051760 cites W3176899693 @default.
- W3213051760 doi "https://doi.org/10.18653/v1/2021.emnlp-main.235" @default.
- W3213051760 hasPublicationYear "2021" @default.
- W3213051760 type Work @default.
- W3213051760 sameAs 3213051760 @default.
- W3213051760 citedByCount "2" @default.
- W3213051760 countsByYear W32130517602022 @default.
- W3213051760 countsByYear W32130517602023 @default.
- W3213051760 crossrefType "proceedings-article" @default.
- W3213051760 hasAuthorship W3213051760A5025796706 @default.
- W3213051760 hasAuthorship W3213051760A5076043621 @default.
- W3213051760 hasAuthorship W3213051760A5084221709 @default.
- W3213051760 hasBestOaLocation W32130517601 @default.
- W3213051760 hasConcept C100279451 @default.
- W3213051760 hasConcept C124101348 @default.
- W3213051760 hasConcept C137293760 @default.
- W3213051760 hasConcept C144986985 @default.
- W3213051760 hasConcept C147168706 @default.
- W3213051760 hasConcept C154945302 @default.
- W3213051760 hasConcept C186644900 @default.
- W3213051760 hasConcept C203005215 @default.
- W3213051760 hasConcept C204321447 @default.
- W3213051760 hasConcept C2777530160 @default.
- W3213051760 hasConcept C2780378701 @default.
- W3213051760 hasConcept C41008148 @default.
- W3213051760 hasConcept C50644808 @default.
- W3213051760 hasConcept C53893814 @default.
- W3213051760 hasConceptScore W3213051760C100279451 @default.
- W3213051760 hasConceptScore W3213051760C124101348 @default.
- W3213051760 hasConceptScore W3213051760C137293760 @default.
- W3213051760 hasConceptScore W3213051760C144986985 @default.
- W3213051760 hasConceptScore W3213051760C147168706 @default.
- W3213051760 hasConceptScore W3213051760C154945302 @default.
- W3213051760 hasConceptScore W3213051760C186644900 @default.
- W3213051760 hasConceptScore W3213051760C203005215 @default.
- W3213051760 hasConceptScore W3213051760C204321447 @default.
- W3213051760 hasConceptScore W3213051760C2777530160 @default.
- W3213051760 hasConceptScore W3213051760C2780378701 @default.
- W3213051760 hasConceptScore W3213051760C41008148 @default.
- W3213051760 hasConceptScore W3213051760C50644808 @default.
- W3213051760 hasConceptScore W3213051760C53893814 @default.
- W3213051760 hasLocation W32130517601 @default.
- W3213051760 hasLocation W32130517602 @default.
- W3213051760 hasOpenAccess W3213051760 @default.
- W3213051760 hasPrimaryLocation W32130517601 @default.
- W3213051760 hasRelatedWork W1569841287 @default.
- W3213051760 hasRelatedWork W1585034923 @default.
- W3213051760 hasRelatedWork W1978971213 @default.
- W3213051760 hasRelatedWork W2167662847 @default.
- W3213051760 hasRelatedWork W2896411932 @default.
- W3213051760 hasRelatedWork W2922463763 @default.
- W3213051760 hasRelatedWork W2955566178 @default.
- W3213051760 hasRelatedWork W3107474891 @default.
- W3213051760 hasRelatedWork W3213051760 @default.
- W3213051760 hasRelatedWork W4309086281 @default.
- W3213051760 isParatext "false" @default.
- W3213051760 isRetracted "false" @default.
- W3213051760 magId "3213051760" @default.
- W3213051760 workType "article" @default.