Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386972857> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W4386972857 endingPage "77" @default.
- W4386972857 startingPage "65" @default.
- W4386972857 abstract "Mongolian morphological analysis (MMA) includes two subtasks: morphological segmentation and morphological tagging. It is a crucial preprocessing step in many Mongolian NLP applications. Recently, end-to-end neural approaches have achieved excellent results in the MMA task. However, these approaches handle morphological segmentation and morphological tagging independently, and ignore the relationship between the two subtasks. In this paper, we propose a multi-task sequence-to-sequence model for the MMA task that learns Mongolian morphological segmentation and tagging jointly. The proposed neural model introduces a shared morphological feature encoder to learn character-level and context-level word information. Besides, we design a flat joint attention decoder and a hierarchical joint attention decoder to generate Mongolian segmentation and tagging results, respectively. We employ the dynamic weight scheme to optimize and balance the weights between the two subtasks in MMA. We compare the proposed model with the baselines and evaluate the effectiveness of the sub-modules in the experiment. The result suggests that the proposed MMA model outperformed the state-of-the-art baselines." @default.
- W4386972857 created "2023-09-23" @default.
- W4386972857 creator A5002561409 @default.
- W4386972857 creator A5009678229 @default.
- W4386972857 creator A5010464164 @default.
- W4386972857 creator A5084054021 @default.
- W4386972857 creator A5086318810 @default.
- W4386972857 creator A5092925023 @default.
- W4386972857 date "2023-01-01" @default.
- W4386972857 modified "2023-09-29" @default.
- W4386972857 title "Multi-task Learning for Mongolian Morphological Analysis" @default.
- W4386972857 cites W1902237438 @default.
- W4386972857 cites W2901397932 @default.
- W4386972857 cites W2943064529 @default.
- W4386972857 cites W2963430933 @default.
- W4386972857 cites W2972720388 @default.
- W4386972857 cites W2996398592 @default.
- W4386972857 cites W3034588688 @default.
- W4386972857 doi "https://doi.org/10.1007/978-3-031-44201-8_6" @default.
- W4386972857 hasPublicationYear "2023" @default.
- W4386972857 type Work @default.
- W4386972857 citedByCount "0" @default.
- W4386972857 crossrefType "book-chapter" @default.
- W4386972857 hasAuthorship W4386972857A5002561409 @default.
- W4386972857 hasAuthorship W4386972857A5009678229 @default.
- W4386972857 hasAuthorship W4386972857A5010464164 @default.
- W4386972857 hasAuthorship W4386972857A5084054021 @default.
- W4386972857 hasAuthorship W4386972857A5086318810 @default.
- W4386972857 hasAuthorship W4386972857A5092925023 @default.
- W4386972857 hasConcept C111919701 @default.
- W4386972857 hasConcept C118505674 @default.
- W4386972857 hasConcept C138885662 @default.
- W4386972857 hasConcept C151730666 @default.
- W4386972857 hasConcept C153180895 @default.
- W4386972857 hasConcept C154945302 @default.
- W4386972857 hasConcept C162324750 @default.
- W4386972857 hasConcept C187736073 @default.
- W4386972857 hasConcept C204321447 @default.
- W4386972857 hasConcept C2776401178 @default.
- W4386972857 hasConcept C2778112365 @default.
- W4386972857 hasConcept C2779343474 @default.
- W4386972857 hasConcept C2780451532 @default.
- W4386972857 hasConcept C34736171 @default.
- W4386972857 hasConcept C35639132 @default.
- W4386972857 hasConcept C41008148 @default.
- W4386972857 hasConcept C41895202 @default.
- W4386972857 hasConcept C54355233 @default.
- W4386972857 hasConcept C86803240 @default.
- W4386972857 hasConcept C89600930 @default.
- W4386972857 hasConcept C90805587 @default.
- W4386972857 hasConcept C98501671 @default.
- W4386972857 hasConceptScore W4386972857C111919701 @default.
- W4386972857 hasConceptScore W4386972857C118505674 @default.
- W4386972857 hasConceptScore W4386972857C138885662 @default.
- W4386972857 hasConceptScore W4386972857C151730666 @default.
- W4386972857 hasConceptScore W4386972857C153180895 @default.
- W4386972857 hasConceptScore W4386972857C154945302 @default.
- W4386972857 hasConceptScore W4386972857C162324750 @default.
- W4386972857 hasConceptScore W4386972857C187736073 @default.
- W4386972857 hasConceptScore W4386972857C204321447 @default.
- W4386972857 hasConceptScore W4386972857C2776401178 @default.
- W4386972857 hasConceptScore W4386972857C2778112365 @default.
- W4386972857 hasConceptScore W4386972857C2779343474 @default.
- W4386972857 hasConceptScore W4386972857C2780451532 @default.
- W4386972857 hasConceptScore W4386972857C34736171 @default.
- W4386972857 hasConceptScore W4386972857C35639132 @default.
- W4386972857 hasConceptScore W4386972857C41008148 @default.
- W4386972857 hasConceptScore W4386972857C41895202 @default.
- W4386972857 hasConceptScore W4386972857C54355233 @default.
- W4386972857 hasConceptScore W4386972857C86803240 @default.
- W4386972857 hasConceptScore W4386972857C89600930 @default.
- W4386972857 hasConceptScore W4386972857C90805587 @default.
- W4386972857 hasConceptScore W4386972857C98501671 @default.
- W4386972857 hasLocation W43869728571 @default.
- W4386972857 hasOpenAccess W4386972857 @default.
- W4386972857 hasPrimaryLocation W43869728571 @default.
- W4386972857 hasRelatedWork W1539050421 @default.
- W4386972857 hasRelatedWork W1582206143 @default.
- W4386972857 hasRelatedWork W2066259560 @default.
- W4386972857 hasRelatedWork W2262783296 @default.
- W4386972857 hasRelatedWork W2380927352 @default.
- W4386972857 hasRelatedWork W2391959412 @default.
- W4386972857 hasRelatedWork W2532775738 @default.
- W4386972857 hasRelatedWork W2964954576 @default.
- W4386972857 hasRelatedWork W3089147131 @default.
- W4386972857 hasRelatedWork W3127509856 @default.
- W4386972857 isParatext "false" @default.
- W4386972857 isRetracted "false" @default.
- W4386972857 workType "book-chapter" @default.