• Refine your search:
  • 
    Keyword:
    
    • Artificial Intelligence cs.AI (2)
    • FOS Computer and information sciences (2)
    • Automatische Textanalyse (1)
    • Automatisches Indexieren (1)
    • Computation and Language cs.CL (1)
    • Information Retrieval cs.IR (1)
    • Wissenserwerb (Künstliche Intelligenz) (1)
  • 
    Creator / Publisher:
    
    • Ma, Chengyuan (3)
    • Guo, Chenlei (2)
    • Aguilar, Gustavo (1)
    • Islam, Md Mofijul (1)
    • Lee, Chin-Hui (1)
    • Liu, Xiaohu (1)
    • Lu, Sixing (1)
    • Mathialagan, Clint Solomon (1)
    • Ponnusamy, Pragaash (1)
    • Sun, Zhongkai (1)
  • 
    Year
  • 
    Medium
  • 
    Type:
    
    • Article (2)
    • Miscellaneous (1)
  • 
    BLLDB-Access

Search in the Catalogues and Directories

All fields Title Creator / Publisher Keyword Year AND OR AND NOT All fields Title Creator / Publisher Keyword Year AND OR AND NOT All fields Title Creator / Publisher Keyword Year AND OR AND NOT All fields Title Creator / Publisher Keyword Year AND OR AND NOT All fields Title Creator / Publisher Keyword Year Sort by creator [A → Z]' creator [Z → A]' publishing year ↑ (asc)' publishing year ↓ (desc)' title [A → Z]' title [Z → A]' Simple Search Hits 1 – 3 of 3 1 A Vocabulary-Free Multilingual Neural Tokenizer for End-to-End Task Learning ... Islam, Md Mofijul; Aguilar, Gustavo; Ponnusamy, Pragaash; Mathialagan, Clint Solomon; Ma, Chengyuan; Guo, Chenlei. - : arXiv, 2022 Abstract: Subword tokenization is a commonly used input pre-processing step in most recent NLP models. However, it limits the models' ability to leverage end-to-end task learning. Its frequency-based vocabulary creation compromises tokenization in low-resource languages, leading models to produce suboptimal representations. Additionally, the dependency on a fixed vocabulary limits the subword models' adaptability across languages and domains. In this work, we propose a vocabulary-free neural tokenizer by distilling segmentation information from heuristic-based subword tokenization. We pre-train our character-based tokenizer by processing unique words from multilingual corpus, thereby extensively increasing word diversity across languages. Unlike the predefined and fixed vocabularies in subword methods, our tokenizer allows end-to-end task learning, resulting in optimal task-specific tokenization. The experimental results show that replacing the subword tokenizer with our neural tokenizer consistently improves ... Keyword: Artificial Intelligence cs.AI; Computation and Language cs.CL; FOS Computer and information sciences URL: https://dx.doi.org/10.48550/arxiv.2204.10815 https://arxiv.org/abs/2204.10815 BASE Hide details 2 Query Expansion and Entity Weighting for Query Reformulation Retrieval in Voice Assistant Systems ... Sun, Zhongkai; Lu, Sixing; Ma, Chengyuan. - : arXiv, 2022 BASE Show details 3 A regularized maximum figure-of-merit (rMFoM) approach to supervised and semi-supervised learning Lee, Chin-Hui; Ma, Chengyuan In: Institute of Electrical and Electronics Engineers. IEEE transactions on audio, speech and language processing. - New York, NY : Inst. 19 (2011) 5, 1316-1327 BLLDB OLC Linguistik Show details

Mobile view All Catalogues UB Frankfurt Linguistik 0 IDS Mannheim 0 OLC Linguistik 1 UB Frankfurt Retrokatalog 0 DNB Subject Category Language 0 Institut für Empirische Sprachwissenschaft 0 Leibniz-Centre General Linguistics (ZAS) 0 Bibliographies BLLDB 1 BDSL 0 IDS Bibliografie zur deutschen Grammatik 0 IDS Bibliografie zur Gesprächsforschung 0 IDS Konnektoren im Deutschen 0 IDS Präpositionen im Deutschen 0 IDS OBELEX meta 0 MPI-SHH Linguistics Collection 0 MPI for Psycholinguistics 0 Linked Open Data catalogues Annohub 0 Online resources Link directory 0 Journal directory 0 Database directory 0 Dictionary directory 0 Open access documents BASE 2 Linguistik-Repository 0 IDS Publikationsserver 0 Online dissertations 0 Language Description Heritage 0